PAPER RADAR · arXiv × Hugging Face · 2026-09-22 → 2026-10-21
What is hot in AI research right now: the last 30 days of papers from arXiv and Hugging Face Daily Papers, ranked by buzz. Every paper has a one-line takeaway and a permanent page; nothing is ever removed from the archive.
#01 ▲748 ★5.5k ❝1 2026-09-27
Raven is an open multi-agent ecosystem that automatically builds, evolves and orchestrates specialised agent harnesses across domains.
EverMind · EverMind AI
#02 ▲220 ★1.6k ❝22 2026-09-21
Adds regularisation to recursive self-improvement of agent harnesses so gains survive out-of-distribution tests.
Google · Peng Xia, Rujun Han, Zifeng Wang +11
#03 ▲223 ★12k ❝1 2026-09-27
YuE2 plans a readable score first and then renders full songs, unifying symbolic and audio music generation.
Multimodal Art Projection · Ruibin Yuan, Jiahao Pan, Junyan Jiang +32
#04 ▲115 ★14k ❝1 2026-10-09
Harness² lets agents recursively improve their own harness on unseen open-world tasks without ground-truth verifiers.
Google · Ruiyao Xu, Yanfei Chen, Zhongying CuiZhu +6
#05 ▲371 ★115 ❝2 2026-10-13
Jeva is a decision-native System 1 model that scores candidate options directly instead of generating text answers, making it fast and cacheable.
National University of Singapore · Qi Li, Xinchao Wang
#06 ▲348 ★187 ❝0 2026-10-14
Player-1 post-trains computer-use agents on synthetic experience so they learn to control games beyond demonstrations.
ARC Lab, Tencent · Mingyu Ouyang, Yiran Wang, Siyuan Hu +9
#07 ▲388 ★116 ❝2 2026-09-28
A survey of in-context learning for robots, grouping methods into four families by how context is turned into action.
Knowin AI · Haojian Huang, Zexi Li, Junhao Guo +36
#08 ▲375 ★210 ❝1 2026-10-13
VideoJev scores time spans and answer options directly, unifying temporal grounding and video QA for fast decisions.
Multimedia Computing Group-Nanjing University · Yuhan Zhu, Xiangyu Zeng, Qingyi Si +15
#09 ▲485 ★200 ❝0 2026-09-25
Omni-IO Skills makes existing agents omni-modal through hierarchical skills, a common execution interface and an asset registry.
National University of Singapore · Yanlin Li, Mingyang Hao, Shengqiong Wu +3
#10 ▲296 ★1.3k ❝0 2026-09-27
VisionHOPE turns a visual backbone into a self-modifying learner whose memory and update rules co-evolve within each image.
Mininglamp Technology · Siran Peng, Tianshuo Zhang, Tianyu Fu +8
#11 ▲459 ★218 ❝0 2026-10-15
Evaluates GPT-6-Astra on 12 robotics benchmarks and discusses what a general model's embodied competence means for the field.
SenseNova · SenseNova, Joint Research Team, Zhongang Cai +59
#12 ▲113 ★2.8k ❝1 2026-10-07
Long-WAM scales the context of world-action models under real-time limits and finds autoregressive video pretraining makes long history pay off.
NVIDIA · Wei Huang, Bohan Zhang, Chenzhi Liu +13
Robotics & embodied AIEfficient training & inference arXiv Code HF
#13 ▲417 ★261 ❝0 2026-09-29
LoopVL brings looped (recurrent) Transformers to vision-language models, iteratively refining a shared vision-language state.
Renmin University of China · Zhe Qian, Ziyang Gong, Zhongxing Xu +13
#14 ▲310 ★140 ❝2 2026-09-30
GroundingPI is a 4B grounding foundation model that outputs points and boxes as tokens to give robots fast, precise targeting.
XPENG AI · Qize Yu, Lianrui Fan, Boyu Chen +23
#15 ▲184 ★200 ❝6 2026-09-12
Realtime-Venus is a full-duplex audio-visual interaction system that listens, watches and talks while delegating tasks asynchronously.
inclusionAI · Ant Group
#16 ▲161 ★512 ❝1 2026-09-21
WorldCrafter adds a camera-queryable implicit 3D memory to a video world model to keep long explorations consistent.
ARC Lab, Tencent · Wangbo Yu, Kunhao Liu, Wenbo Hu +8
#17 ▲238 ★228 ❝3 2026-10-01
OneStreamer lets streaming video LLMs keep hierarchical caption memories and respond proactively once evidence is sufficient.
Nanjing University · Xiangyu Zeng, Yuandong Yang, Zhiqiu Zhang +21
#18 ▲364 ★312 ❝0 2026-10-14
ATAS compiles screenplays into shots backed by scene and event memories so long agentic videos stay spatially and temporally consistent.
Zhejiang University · Weijie Wang, Haomin Zhang, Ye Li +7
#19 ▲330 ★396 ❝0 2026-10-15
OpenGCUA aims to open the full stack for generalist computer-use agents, with a first release spanning GUI and code execution.
Tongyi-MAI · Hanzhang Zhou, Long Li, Quyu Kong +12
#20 ▲293 ★201 ❝1 2026-10-08
AgentGarten couples simulators and game engines with a neural renderer to build faithful, realistic worlds for training agents.
MirroS · Jiawei Chi, Shangchen Miao, Zhiyuan Shi +12
#21 ▲240 ★227 ❝0 2026-09-19
OmniEdu is an open family of K-12 education foundation models covering problem solving, curriculum grounding, diagnosis and tutoring.
Peking University · Hao Liang, Qihan Lin, Meiyi Qiang +5
#22 ▲511 ★7 ❝2 2026-09-29
Extrapolates RL-induced hidden-representation residuals in on-policy distillation so students can surpass teachers more stably.
Affiliation unverified · Hao Li, MeiJia Chen, Weijie Ren +4
Efficient training & inferenceReinforcement learning arXiv Code HF
#23 ▲272 ★107 ❝0 2026-10-15
FDE-Gym offers 95 real delivery tasks testing whether agents can clarify vague requirements and ship working solutions like forward-deployed engineers.
DeepLethe · Dongxu Yang, Hongda Yan, Renxin Wang +23
#24 ▲325 ★154 ❝0 2026-10-08
DiffusionART aggregates rewards before tilting the objective, making online RL fine-tuning of diffusion models efficient and stable.
KlingAI Research · Zhenglin Wan, Jiayu Chen, Zhengfeiyang Zhang +6
#25 ▲490 ★30 ❝0 2026-10-14
BizBench, built on real payment procedures, checks whether long-horizon agents violate policies and constraints mid-execution.
ant-international · Enhan Zhao, Yongqi Tong, Xuejun Yu +6
#26 ▲727 ★5 ❝0 2026-10-15
ReviewFact labels factual errors in peer reviews; PremiseCheck combines an LLM with cheap decision models to verify them efficiently.
Affiliation unverified · Dingjie Song, Zhiling Yan, Ziqian Zhang +2
Benchmarks & dataEfficient training & inference arXiv Code HF
#27 ▲560 ★17 ❝0 2026-10-15
MJev-Spatial casts spatial questions as classification over candidates, answering relation, distance and point queries faster than text generation.
Mind Lab · Luozheng Qin, Yuhan Zhu, Changhai Zhou +9
#28 ▲367 ★36 ❝1 2026-09-28
MaLiang-Harness has MLLMs generate images and videos via programs in a build-inspect-revise loop that closes the program-to-visual gap.
National University of Singapore · Haoyu Zhao, Zihao Zhang, Xudong Wang +4
#29 ▲642 ❝2 2026-09-30
Identifies co-cheating in self-evolving search agents, where proposer and solver converge on shared errors, and mitigates it with multi-sample verification.
Rutgers University · Meijia Chen, Hao Li, Zheng Lu +12
#30 ▲602 ★7 ❝0 2026-10-14
LEV lets decision models think deeper by looping their layers instead of generating reasoning tokens.
Affiliation unverified · Dingjie Song, Zhiling Yan, Yuxuan Zhang +1
#31 ▲217 ★297 ❝0 2026-10-13
Formalises self-evolving agent harnesses and derives generalisation and retention bounds for the process.
ZGCAGI · Chuyang Wei, Haoxiang Guan, Minghang Zhu +5
#32 ▲313 ★84 ❝0 2026-10-16
HexaShell keeps the harness thin so a coding agent drives a two-arm robot via a command line and writes its own tools after failures.
HexaFuture · Hongcheng Gao, Alex Zhou, Jay Zhu +13
#33 ▲270 ★175 ❝0 2026-10-09
Finds S-Space, a linear subspace inside MLLMs where object tokens encode continuous coordinates, acting as an internal spatial workspace.
MirroS · Zhiyuan Shi, Xiang Li, Xingzhuo Guo +8
#34 ▲163 ★36 ❝1 2026-09-22
Taste-Bench measures an agent's 'taste' for long-horizon decisions and explores ways to improve it.
Microsoft · Wenbo Pan, Zhichao Liu, Shujie Liu +6
#35 ▲273 ★18 ❝0 2026-09-24
Shows post-training leaves behavioural shadows in unrelated outputs; a single teacher word per prompt can transfer capabilities to a student.
Peking University · Ziyang Zhang, Yubin Jing, Yuanhao Zeng +3
#36 ▲224 ★47 ❝0 2026-09-28
Shows latent visual reasoning tokens barely respond to image evidence and proposes grounding them in visual evidence during training.
Amazon · Xi Xiao, Tianchen Zhao, Youngeun Kim +10
#37 ▲214 ★234 ❝0 2026-10-13
Agent-Reflex trains agents in three stages to reflect proactively and recover when tool feedback is noisy or users intervene.
NLPIR Lab @ RUC · Guanting Dong, Xinyu Yang, Jiajie Jin +9
#38 ▲21 ★2.8k ❝22 2026-09-29
TabFM is a 400M-parameter tabular foundation model trained on synthetic tables that predicts zero-shot in a single forward pass.
Google · Weihao Kong, Erez Louidor Ilan, Shuxin Nie +6
#39 ▲174 ★364 ❝0 2026-10-04
Kandinsky 6.0 Video generates 5-second clips with synchronised 44 kHz audio and lip-sync, in 3B and 29B variants.
Kandinsky Lab · Team Kandinsky, Julia Agafonova, Bulat Akhmatov +85
#40 ▲167 ★97 ❝0 2026-09-23
Builds 150 cognitive-science tasks to test and train object permanence in video world models.
Carnegie Mellon University · Haotian Zhang, Fengyuan Yu, Dezhi Luo +28
#41 ▲167 ★303 ❝0 2026-10-08
REMORY appends learned soft memory tokens after a summary so long-horizon agents lose less when compacting context.
Fusion Lab: Generative Vision Lab of Fudan University and SII · Hanchen Xia, Baoyou Chen, Yutang Ge +5
#42 ▲116 ★1.6k ❝0 2026-10-06
nanoMuse is an open-source personal agent that spans a user's devices and accounts, positioned as an open counterpart to Meta's Muse.
Zhejiang University · Guangyi Liu, Yong Liu, Jiangning Zhang
#43 ▲241 ★9 ❝0 2026-10-08
Shows LLMs keep reasoning even when told not to think, and proposes a three-level way to measure no-thinking behaviour.
Stanford University · Dianqiao Lei, Kevin Qinghong Lin, Pan Lu +2
#44 ▲197 ★123 ❝0 2026-10-07
UltraText Bench uses 432 bilingual prompts to evaluate dense visual text rendering in image generators.
Westlake University · Deyuan Liu, Yihao Hu, Jingxuan Zhang +13
#45 ▲140 ★82 ❝0 2026-09-28
Finds latent world-action models lose the generalisation benefits of explicitly generating future frames at test time.
Tsinghua-LeapLab · Renping Zhou, Zanlin Ni, Zihao Fan +8
#46 ▲137 ★114 ❝0 2026-10-13
AesCode uses a generated image as aesthetic guidance and decoupled cross-modal rewards to produce better-looking slides and posters as code.
Microsoft · Xin Gao, Yifan Yang, Xin Li +13
Code & SWEVisual generationReinforcement learning arXiv Code HF
#47 ▲181 ★57 ❝1 2026-09-28
Normalises each teacher's feedback strength by domain in multi-teacher on-policy distillation so one student learns maths, code and instruction following.
Nanyang Technological University · Xin Li, Hao Jiang, Xin Gao +6
Efficient training & inferenceReinforcement learning arXiv Code HF
#48 ▲47 ★742 ❝2 2026-09-29
Context Language Models treat their context as an editable file and decide what to keep, gaining accuracy with fewer FLOPs.
Meta · Rulin Shao, Shannon Zejiang Shen, Junjie Oscar Yin +10
#49 ▲131 ★523 ❝0 2026-10-14
InfiniSplat v2 analyses and improves feed-forward 3D Gaussian reconstruction for better rendering under large viewpoint changes.
zju3dv · Yongzhen Hu, Hao Yu, Jiawei Wang +7
#50 ▲78 ★526 ❝0 2026-09-21
GAE reparameterises geometry foundation-model features into a compact latent space so generated worlds stay 3D-consistent.
ARC Lab, Tencent · Jiahao Lu, Minghao Yin, Wenbo Hu +5
#51 ▲143 ★63 ❝0 2026-10-08
TokenRouter is a serving system for token-level LLM routing that fixes step desynchronisation and batching delays.
Tsinghua-NICS-EFC · Tianyu Fu, Tengxuan Liu, Ruoxi Wang +4
#52 ▲133 ★105 ❝0 2026-10-13
Urbex treats city-scale 3D grounding as active search by a VLM agent that zooms and changes views, optimised with RL.
alibaba · Yu Wang, Rui Dai, Wei Chen +5
#53 ▲233 ★42 ❝0 2026-10-09
AgentSWE benchmarks whether coding agents can create, edit and optimise agents that truly meet the stated requirement.
Affiliation unverified · Jiahao Wang, Hongjin Qian, Yuyang Hu +2
#54 ▲112 ★54 ❝4 2026-09-28
Argues for expressing robot tasks as inspectable, revisable code so self-evolving coding agents can move into the physical world.
HexaFuture · Hongcheng Gao, Jingjing Zhou, Zelin Zheng +10
#55 ▲73 ★572 ❝0 2026-09-21
GameHorizon provides multi-horizon gameplay data and evaluation to measure planning and control across model families.
Tencent · Yiran Wang, Xingyilang Yin, Junfu Pu +12
#56 ▲89 ★1.2k ❝0 2026-10-16
MOSS-Image is an open 5B text-to-image system strong at bilingual long-text rendering and layouts, with intent-aware prompt enhancement.
OpenMOSS · MOSI. AI
#57 ▲101 ★56 ❝1 2026-10-02
DuoMatching matches both joint and per-frame marginal distributions to improve quality and alignment in few-step video generation.
ByteDance · Jiahao Zhan, Yan Wang, Yongrui Ma +5
Visual generationEfficient training & inference arXiv Code HF
#58 ▲94 ★78 ❝4 2026-09-30
GroundAnything decodes grounding outputs in parallel with bidirectional diffusion, keeping precision while being much faster.
XPENG AI · Qize Yu, Lianrui Fan, Bowen Ping +19
#59 ▲83 ★131 ❝3 2026-10-01
UniWAM unifies a physical reasoner, a world generator and an action predictor in one model for robot control.
HKUSTGZ · Wenxuan Song, Jiayi Chen, Jingbo Wang +13
#60 ▲119 ★272 ❝0 2026-10-19
MemT-1.0 makes memory intrinsic to the model using Gated DeltaNet-2 and Mixture-of-Storage to scale native memory.
MemTensor · Zhiyu Li, Zeyu Zhang, Linyun Liu +71
#61 ▲102 ★152 2026-10-19
OpenVLHarness gives MLLMs a tool capability layer and persistent multimodal memory for visual tasks needing external evidence.
Apple · Yu Zhou, Cheng-Fu Yang, Rui Sun +8
#62 ▲143 ★30 ❝0 2026-10-10
Dynamic Band Splitting adapts frequency band boundaries per mixture to improve audio source separation within a fixed token budget.
Tsinghua Machine Learning Group · Bingzhe Zhang, Kai Li, Xiaolin Hu
#63 ▲155 ★19 ❝0 2026-10-13
Into the Unknown asks agents to write follow-up papers on unpublished directions from US national-lab scientists to test open research ability.
Carnegie Mellon University · Seungone Kim, Jiayi Geng, Young-Jun Lee +25
#64 ▲291 ★5 ❝0 2026-10-16
OR-License benchmarks whether LLM agents can turn original client materials from 31 paid operations-research engagements into expert-grade solutions.
ALLE AI · Peisong Wang, Feixue Liu, Yize Meng +16
#65 ▲34 ★637 ❝9 2026-09-29
Systematically tests GPT-6 Astra as an embodied policy across six domains, alone and combined with learned policies.
Galbot · Galbot Team, Xuchuan Chen, Xiaoqian Cheng +31
#66 ▲92 ★32 ❝1 2026-10-01
PoS has agents maintain explicit belief states of the world and open requirements, avoiding belief traps in long tasks.
alibaba · Yu Luo, Jiamin Jiang, Yimin Zuo +9
#67 ▲116 ★59 ❝0 2026-09-29
GEB groups observations of the same physical object into entity biographies to answer questions over long videos.
Amazon Science · Hui Ren, Lei Fan, Henry Pao +5
#68 ▲189 ★10 ❝1 2026-10-06
Self-Retrospection Distillation turns hindsight into foresight supervision, filling the gap when RLVR rewards are all identical.
Salesforce AI Research · Haoxiang Zhang, Qinglin Chen, Hiroaki Hayashi +9
#69 ▲54 ★809 ❝2 2026-10-09
RSI-Anything uses predictive world models to guide actions and data selection for domain-general recursive self-improvement.
PhAI Labs · Taoyong Cui, Pinxian Zeng, Wanghan Xu +8
#70 ▲218 ★10 ❝0 2026-10-15
Waypoint-OPD uses an intermediate teacher checkpoint to transfer only consistent RL-induced policy shifts to the student.
Affiliation unverified · Bingxi Hou, Guochao Jiang, Guofeng Quan +4
Reinforcement learningEfficient training & inference arXiv Code HF
#71 ▲225 ★12 ❝0 2026-10-19
FocusGUI is a lightweight adapter that picks the step-relevant omni-modal evidence for a frozen GUI agent, curbing compounding distraction.
Nanyang Technological University · Fuyao Zhang, Wenwen He, Jiaming Zhang +6
#72 ▲179 ★36 ❝0 2026-10-19
Ropedia W0 is an egocentric loco-manipulation world foundation model spanning humans and robots, trained on 10k hours of human and 3k hours of robot data.
Ropedia · Tianqi Liu, Hanfei Zhao, Qifeng Liang +12
#73 ▲131 ★101 ❝0 2026-09-29
STEPQuant studies where and when quantisation errors matter in linear-attention recurrent states, enabling low-precision state storage.
Zhejiang University · Bingchen Yao, Haobo Xu, Haokun Lin +6
#74 ▲117 ★185 ❝0 2026-10-15
3DCodeVerse offers 2M executable 3D programs and a coding harness so agents can create editable, verifiable 3D content.
University of Southern California · Yipeng Gao, Ziyao Zeng, Jinfa Huang +16
#75 ▲38 ★115 ❝6 2026-09-21
Harness-Zero distils the gains of specialised agent harnesses into model weights so they persist under a single fixed harness.
Peking University · Haoran Ye, Yuxing Lu, Haonan Dong +2
#76 ▲63 ★210 ❝3 2026-09-30
A survey of post-training and alignment for video generation, covering temporal coherence, physics and safety challenges.
Arizona State University · Chaoyu Li, Xiaoyi Gu, Yogesh Kulkarni +10
#77 ▲205 ❝1 2026-09-28
A controlled study isolating on- vs off-policy rollouts in distillation, finding a more nuanced picture than 'on-policy is always better'.
University of Cambridge · Julianna Piskorz, Antonin Berthon, Mihaela van der Schaar
#78 ▲266 ❝0 2026-09-30
UniEvo-VL has one multimodal model act as both teacher and student, using its own critiques for on-policy self-distillation.
Stanford NLP · Fang Wu, Da Xing, Yanjie Huang +16
#79 ▲151 ★70 ❝0 2026-09-28
PanoVLN studies how to make vision-and-language navigation actually benefit from panoramic observations.
Zhejiang University · Zhen Wang, Changpeng Wang, Zhe Liu +5
#80 ▲153 ★13 ❝1 2026-10-06
Learn2Play Bench uses text games with novel or counterintuitive rules to test whether agents learn from experience.
National University of Singapore · Yibo Li, Jinhang Qiu, Zhi Zheng +4
#81 ▲75 ★763 ❝0 2026-09-26
MALA attention allocates post-score computation by normalised contribution, skipping negligible work to save compute.
Beijing Academy of Artificial Intelligence · Jingze Shi, Zhangyang Peng, Xianduo Li +6
#82 ▲30 ★224 ❝19 2026-09-21
Jev-Mem uses a fast System 1 control plane to manage agent memory, removing costly generation from the critical path.
Affiliation unverified · Dongming Jiang, Yi Li, Bingzhe Li
#83 ▲97 ★74 ❝1 2026-10-06
Recursive Game Creator iterates with designer, builder, player and reviewer roles so agents make games that are actually fun.
The University of Hong Kong · Jiajun Chen, Haoyu Wu, Mingda Jia +1
#84 ▲62 ★102 ❝1 2026-09-28
Studies looped transformers under test-time scaling and proposes adaptive looping to beat baselines at matched compute.
Tsinghua-NICS-EFC · Yichen You, Tianyu Fu, Aosong Feng +4
#85 ▲138 ★17 ❝1 2026-09-25
FuseReg learns regularised layer fusion to ease the reconstruction-generation trade-off in representation autoencoders.
USC Physical Superintelligence (PSI) Lab · Hongyang Du, Yunfei Xie, Junjie Ye +13
#86 ▲111 ★30 ❝0 2026-10-01
Finds a 'sharpening tax': pre-trained LLMs with a light harness often beat post-trained ones on agentic coverage despite lower pass@1.
Meta · Changdae Oh, Qi Zeng, Qi Qi +7
#87 ▲103 ★114 ❝0 2026-09-22
SpeakerMem-R1 builds speaker-centred dual-track memory for multi-party dialogue, tracking who said what about whom.
Zhejiang University · Haobo Zheng, Tan Tang, Yan Chen +2
#88 ▲154 ★34 ❝0 2026-10-08
Reflex enables humanoids to react with whole-body control from egocentric vision, such as catching a thrown box.
University of Washington · Taoyang Jia, Weikai Huang, Linxin Song +6
#89 ▲149 ★38 ❝0 2026-10-14
MAI-Gym is an open all-in-one GUI agent platform unifying evaluation, data collection and online RL at up to 20,000 parallel environments.
Tongyi-MAI · Panrong Tong, Quyu Kong, Pengxiang Li +12
#90 ▲327 ❝0 2026-09-26
Studies scaling of same-family on-policy distillation, finding accuracy rises roughly linearly with KL distance early in training.
Zhejiang University · Yuntai Bao, Qinfeng Li, Guoqing Jiang +5
Efficient training & inferenceReinforcement learning arXiv HF
#91 ▲110 ★113 ❝0 2026-10-14
Doc2Harness directly benchmarks whether LLMs can engineer a long-horizon coding-agent harness from a development document.
Institute of Computing Technology · Yuyao Ge, Shenghua Liu, Peizhong Gao +8
#92 ▲67 ★763 ❝0 2026-09-26
CoWA attention splits long-range history across KV heads so each is sparse yet together they cover the full causal context.
Beijing Academy of Artificial Intelligence · Jingze Shi, Zhangyang Peng, Xianduo Li +6
#93 ▲170 ★18 2026-10-19
EgoXperience jointly reconstructs observer motion, scene geometry and hand-object interaction from egocentric video, with an auto-annotation engine and benchmark.
Ropedia · Xinhao Ji, Hui En Pang, Hao Li +12
Vision & 3DRobotics & embodied AIBenchmarks & data arXiv Code HF
#94 ▲74 ★100 ❝0 2026-10-12
Multics generates multi-player world videos with hierarchical player-group-global communication that scales to more players.
ARC Lab, Tencent · Kaiyi Huang, Wangbo Yu, Yukun Huang +6
#95 ▲134 ★39 ❝0 2026-09-29
AREX-2 trains on long improvement trajectories from ML and algorithm tasks so agents iteratively refine solutions at test time.
Beijing Academy of Artificial Intelligence · Hongjin Qian, Chaofan Li, Kun Luo +11
#96 ▲119 ★75 ❝0 2026-10-05
Trace2Env lets a world-model agent role-play an environment reconstructed from historical traces for training and evaluating agents.
Nanyang Technological University Singapore · Quanyu Long, Xiao Chen, Jianda Chen +4
#97 ▲74 ★49 ❝3 2026-10-01
PROWBench tests whether video models faithfully render program-specified world events, aimed at next-gen game engines.
Alaya Lab · Zheng-Hui Huang, Guixu Lin, Yu-Ju Tsai +6
#98 ▲97 ★146 ❝0 2026-09-30
RSIGame improves agent-built games with local and global recursive loops to avoid overfitting a few test cases.
RSIGame · Wenyi Wu, Minghao Fu, Jieyu You +10
#99 ▲206 ★6 ❝0 2026-10-13
RoTA-Bench evaluates VLMs' 3D spatial reasoning by having them rotate objects to match target silhouettes interactively.
MAC-AutoML · Qingchuan Ma, Yuexiao Ma, Xiang Meng +7
#100 ▲64 ★574 ❝0 2026-10-20
Sage-A1.5 is a 35B MoE agentic model adding subagent orchestration, self-verification and open-ended scientific exploration.
Intern Science · Wenjie Lou, Tianshuo Peng, Shiyang Feng +96
#101 ▲76 ★56 ❝0 2026-10-10
Builds 450 tasks from 150 real vulnerabilities to check whether code written by vibe-coding agents is secure.
Qwen · Tianyi Wu, Chao Ge, Peng Chen +12
Code & SWESafety & interpretabilityBenchmarks & data arXiv Code HF
#102 ▲70 ★91 ❝0 2026-10-06
VisionWeave lets MLLMs learn end-to-end where and how finely to spend visual tokens, adapting to image content.
Qwen · Yuan Feng, Qize Yang, Ruizhe Chen +9
#103 ▲86 ★198 ❝0 2026-10-08
SuperNav lets an MLLM interpret requests and decide while delegating motion to navigation tools, generalising across tasks and scenes.
zju3dv · Jinkai Zhang, Jingyi Xu, Yuanhong Yu +5
#104 ▲80 ★49 ❝0 2026-10-03
ALoDLM adds token-adaptive latent recurrence to diffusion language models, narrowing the quality gap with autoregressive models.
Amazon · Liancheng Fang, Zhuowei Li, Youngeun Kim +10
#105 ▲44 ❝40 2026-09-22
Uses a decision-only judge as a cheap first pass and escalates to stronger judges only when unsure.
Carnegie Mellon University · Yubo Li, Yidi Miao, Ramayya Krishnan +1
#106 ▲124 ★30 ❝0 2026-09-30
FrameMorrow selects history frames by future relevance via prospective tokens for efficient, consistent long video generation.
National University of Singapore · Bo Yin, Xiaobin Hu, Jiaqi Zhao +1
Visual generationEfficient training & inference arXiv Code HF
#107 ▲156 ★13 ❝0 2026-10-19
Holi-World is an ecosystem for learning world intelligence from human egocentric experience, from capture to evaluation.
Ropedia · Hao Li, Xiyuan Zheng, Yuanyuan Gao +7
#108 ▲75 ★287 ❝0 2026-10-08
LeWAM is an end-to-end JEPA world-action model that supports both direct policy execution and efficient planning.
LeWAM · Minghao Fu, Tavis Siebert, Eryk Halicki +1
#109 ▲30 ★2.1k ❝0 2026-10-06
NeMo-DCR syncs only the ~1% of weights that change per step, bit-exactly, to speed trillion-parameter agentic RL refits.
NVIDIA · Songlin Jiang, Zhiyu Li, Terry Kong +5
Efficient training & inferenceReinforcement learning arXiv Code HF
#110 ▲78 ★38 ❝2 2026-09-29
Imagine3D-LLM teaches MLLMs to imagine a 3D scene before answering multi-view spatial questions.
KAIST AI · Jaewoo Jung, Hyeonseo Yu, Honggyu An +10
#111 ▲92 ❝6 2026-10-08
Technical report of Xiaomi's omni-modal MiMo-V2.6, focused on scaling RL compute along several dimensions toward self-improvement.
Xiaomi MiMo · Xiaomi LLM-Core Team, :, Zongming Qiao +147
#112 ▲63 ★75 ❝0 2026-10-01
VeriHarness turns the base model into a verification agent that uses disagreement across samples to decide which claims to trust.
Google · Caiqi Zhang, Rujun Han, Zifeng Wang +4
#113 ▲92 ★83 ❝0 2026-10-14
Compares ten agentic-RL self-distillation methods against GRPO under identical conditions to check real gains and costs.
Zhejiang University · Linhao Zhong, Bozhen Fang, Xuehao Wang +7
#114 ▲102 ★12 ❝0 2026-10-07
VIS-Ground lets viewers steer interactive video stories while staying consistent with the source and rendered history.
Google · Bingxuan Li, Yiwen Song, Xueqing Wu +10
#115 ▲52 ★51 ❝5 2026-10-01
Has robot agents compose primitives into locally retried Python cells, raising success while cutting token use.
DAGroup-PKU · Ruiyang Si, Jianxin Bi, Shunyu Yang +12
Robotics & embodied AIAgentsEfficient training & inference arXiv Code HF
#116 ▲287 ❝0 2026-10-01
RealCompanion releases ten real AI-companion relationships (27,218 messages over up to 120 days) to test long-term understanding of a person.
Quis Lab · Arman Behnam, Sunglyoung Kim, Jiayi Yu +2
#117 ▲105 ❝3 2026-10-02
Recursive Self-Rewrite finds solutions under specialised harnesses and rewrites them as training trajectories for a general harness.
Tencent Hunyuan · Zongxia Li, Yucheng Shi, Zhongzhi Li +7
#118 ▲32 ★945 ❝0 2026-10-06
The Recurrent Looped Transformer lets compute depth grow with sequence length, generalising tasks like parity far beyond training length.
Princeton University · Yifan Zhang, Jichen Feng, Shihan Qin +2
#119 ▲120 ❝1 2026-09-30
Mid-Harness samples and verifies candidate actions before execution, improving terminal-agent reliability.
NVIDIA · Minki Kang, Ryo Hachiuma, Shaokun Zhang +8
#120 ▲251 ❝0 2026-10-09
Adds cross-teacher guarding to multi-teacher on-policy distillation to reduce gradient conflicts between domain teachers.
jingdong · Shi-Yu Tian, Yong Liu, Ximan Liu +10
#121 ▲89 ❝11 2026-09-19
RoboDawn exposes robot control as simple discrete commands to an agentic VLM, testing whether digital intelligence transfers to the physical world.
Affiliation unverified · Meng-Hao Guo, Zhe-Han Mo, Jia-Jun Wang +6
#122 ▲92 ★62 ❝0 2026-10-01
Hierarchical continuous diffusion LMs tie the denoised continuous state to valid tokens, improving coherence of parallel decoding.
University of Illinois at Urbana-Champaign · Hui Ren, Zihan Li, Chang Liu +2
#123 ▲38 ★386 ❝0 2026-10-13
Hybrid Reasoning Agents switch dynamically between latent reasoning and text interaction, combining efficiency with tool access.
Stanford University · Jiaru Zou, Yunzhe Qi, Sirui Chen +5
#124 ▲104 ★35 ❝0 2026-09-29
The Thinking Reward Model first sets case-specific rubrics and then scores, giving finer rewards for visual generation.
Affiliation unverified · Xuehai Bai, Zhenchen Tang, Yang Shi +9
#125 ▲55 ★63 ❝0 2026-09-21
onPanda is an annotation tool where annotators fix the first bad token and let the model continue, cheaply producing alignment data.
StepFun · Lei Yang, Mengyin Liu, Jia Wang +9
#126 ▲52 ★103 ❝0 2026-10-13
LensErase is a general erase-anything model trained on 100M pairs, removing objects, text, watermarks and their visual effects.
Microsoft · Yunuo Chen, Xiuyu Wu, Qinhong Yang +11
#127 ▲34 ★227 ❝1 2026-09-29
PixelUMM unifies image and video understanding and generation directly in pixel space without a visual encoder.
NVIDIA · Cong Wei, Xuanchi Ren, Bryan Chu +8
#128 ▲88 ★51 ❝0 2026-09-20
Proposes Grounded Action Models, robot foundation models built on 3D grounding and promptable with language, points or boxes.
National University of Singapore · Gehao Zhang, Weikai Huang, Shailesh Shailesh +3
#129 ▲237 ❝0 2026-10-19
Uses parameter-efficient fine-tuning to adapt multimodal backbones of up to 104B for brain encoding, better predicting neural responses.
Mind Lab · Zhuofan Josh Ying, Guanglong Sun, Nolan Ho +6
#130 ▲165 ❝0 2026-10-09
Scales synthesis of high-quality long-horizon terminal trajectories to train agents for professional tasks.
alibaba · Shun Zou, Ziyu Ma, Yi Zou +6
#131 ▲76 ★34 ❝1 2026-10-04
SearchJev is a fast, calibrated System 1 model that makes relevance and action decisions for search agents.
Affiliation unverified · Congfeng Cao, Lipeng Zuo, Konstantinos Papakostas +6
#132 ▲132 ★9 ❝0 2026-10-07
LiveMACE uses live financial markets to evaluate persistent LLM agents on both outcomes and process diagnostics.
Fudan University · Jun Zhao, Leiming Fu, Yanbo Wen +9
#133 ▲110 ★23 ❝0 2026-10-15
Introduces SAR to measure whether sparse-autoencoder features compose additively in downstream behaviour, aiding interpretability.
OpenSAE · Haotian Ma, Ziye Mei, Frederic Sala
#134 ▲34 ★178 ❝4 2026-10-02
4DCodeBench asks agents to reconstruct dynamic scenes from video as executable graphics programs.
4DCodeBench · Ruihong Shen, Žiga Kovačič, Peter Kulits +6
#135 ▲47 ★215 ❝1 2026-10-20
SolarRenderer adds two LoRAs to a frozen video model to render coarse structural video into realistic footage in four steps, including real-time streaming.
Show Lab · Guian Fang, Shengju Qian, Dongyue Lu +6
Visual generationEfficient training & inference arXiv Code HF
#136 ▲60 ★207 ❝0 2026-10-07
SGF+ separates parameters for context writing and denoising in autoregressive video generation to resolve conflicting gradients.
Affiliation unverified · Zihan Su, Junhao Zhuang, Yaowei Li +10
#137 ▲111 ★20 ❝0 2026-10-08
SoftwareGym automatically synthesises diverse, executable, verifiable GUI software environments to scale computer-use agent training.
Shanghai Jiao Tong University · Tian Jin, Wenhao Wang, Jing Kang +4
#138 ▲88 ★30 ❝0 2026-10-10
Vela uses real long-term user behaviour records as supervision to improve LLMs at inferring preferences, intent and future actions.
AllSpark Research · Yang Xiao, Yusong Sun, Haoyi Wu +17
#139 ▲152 ❝0 2026-10-05
LoGRA cuts RL post-training memory with low-rank gradient sketches and keeps training stable with predicted-KL step control.
NVIDIA · Shaokun Zhang, Yifan Zhang, Jian Hu +5
Reinforcement learningEfficient training & inference arXiv HF
#140 ▲89 ★34 ❝0 2026-10-01
World Observer jointly generates panoramic observer views alongside the actor view so off-screen objects keep evolving consistently.
KAIST AI · Hyunwook Choi, Dahyun Chung, Hyunsung Kim +4
#141 ▲112 ★7 ❝1 2026-09-30
EvoDuet co-evolves solutions and web-search queries in a bilevel loop so LLM evolutionary search doesn't stall for lack of knowledge.
Minnesota NLP · Young-Jun Lee, Jinheon Baek, Soyeong Jeong +5
#142 ▲72 ★104 ❝0 2026-10-01
ViGAR splits long-horizon manipulation into a visual subgoal planner and a subgoal executor for compositional, in-context robot tasks.
DAGroup-PKU · Shukai Gong, Xuanran Zhai, Yintianrun Zhang +16
#143 ▲51 ★81 ❝0 2026-10-14
Intern Lumina U2 is a multi-codebook diffusion LLM unifying visual understanding and image generation in one space.
Shanghai AI Laboratory · Qian Yu, Zongyang Qiu, Juncheng Yan +40
#144 ▲33 ★141 ❝4 2026-09-21
A survey of LLMs in mental health, tracing the evolution from pattern recognisers to personalised companions.
Affiliation unverified · He Hu, Yucheng Zhou, Qianning Wang +8
#145 ▲43 ★48 ❝1 2026-10-14
Orbia is a benchmark for 3D consistency of interactive world models, testing whether scenes persist on revisits.
Tencent · Dongyue Lu, Guian Fang, Hur Lim +20
#146 ▲134 ★7 ❝0 2026-09-26
VoxMem benchmarks whether audio LLMs remember who said what, how, and what was audible—information beyond the transcript.
The University of Melbourne · Yang Xiao, Vidhyasaharan Sethu, Eun-Jung Holden +1
#147 ▲92 ★28 ❝0 2026-09-22
Disaggregated quantisation specialises formats and weights for prefill and decode separately to balance speed and accuracy.
IST Austria Distributed Algorithms and Systems Lab · Andrei Panferov, Maximilian Kleinegger, Sweta Priyadarshi +2
#148 ▲60 ★135 ❝0 2026-10-13
OmniCompass evaluates video grounding and understanding on separate vision-language and audio-visual tracks.
VCLab · Xuyang Liu, Shihao Wang, Xinyu Wei +5
#149 ▲64 ★44 ❝1 2026-10-08
OuroWorld turns any static 3D Gaussian scene into a seamlessly looping 3D cinemagraph viewable from any angle.
Alaya Lab · You-Zhe Xie, Ting-Wei Chou, Yu-Hsuan Li +3
#150 ▲140 ❝0 2026-09-29
Adaptive Reward Routing dynamically adjusts where updates act and how rewards combine to improve joint audio-video diffusion.
Tencent · Songlin Yang, Xiaotong Zhao, Jiacheng Zhang +5
#151 ▲96 ★21 ❝0 2026-10-12
TPPO uses a cumulative value parameterisation to track value along the trajectory, improving token-level credit in PPO for reasoning.
Affiliation unverified · Futing Wang, Chenxi Li, Jianhao Yan +6
#152 ▲64 ★90 ❝0 2026-09-19
Spatial-Interactor trains VLM spatial reasoning on observation-action-observation interaction trajectories.
ZJU-OmniAI · Kaixiang Yao, Xu Wang, Miao Pan +10
#153 ▲90 ★26 ❝0 2026-10-07
GRACE further compresses the video latent while staying compatible with the pretrained DiT, speeding up video generation.
KAIST AI · Jiyoung Kim, Paul Hyunbin Cho, Jisu Nam +5
Visual generationEfficient training & inference arXiv Code HF
#154 ▲64 ★20 ❝0 2026-10-14
ActionOPD distils agents at the level of semantic actions rather than tokens to transfer decisions to smaller models.
Tsinghua-NICS-EFC · Huining Yuan, Xiangmin Yi, Zelai Xu +5
#155 ▲77 ★58 ❝0 2026-09-21
Ovis-Embedding encodes text, images, video and audio into one shared embedding space using an omni-modal backbone.
ATH-MaaS · Ovis-Embedding Team
#156 ▲84 ★40 2026-10-19
ScaleNav learns goal-directed visual dynamics from internet egocentric videos for language-conditioned robot navigation.
Affiliation unverified · Yihui Yang, Yuanhong Yu, Jiawei Wang +7
#157 ▲50 ★45 ❝0 2026-09-20
Trains category-specific SWE experts and then integrates them, easing the see-saw across task categories in pooled RL.
alibaba · Jie Zhao, Ziyu Jiang, Suhang Zheng +3
#158 ▲86 ★11 ❝1 2026-09-29
Has a Builder model learn meta-skills to construct better harnesses for a fixed Target model at test time (AI-for-AI).
Apodex · Cheng Qian, Kunlun Zhu, Beibin Li +2
#159 ▲93 ★21 ❝0 2026-10-15
Speculative Forcing treats intermediate estimates as drafts and accepts converged tokens early to speed up autoregressive video generation.
NAVER AI Lab · Hyunwook Choi, Seungryong Kim, Dongyoon Han +1
Visual generationEfficient training & inference arXiv Code HF
#160 ▲68 ★22 ❝0 2026-09-30
Shows weighted-sum rubric rewards can be hacked (e.g. in clinical consultation) and proposes protocol-level rubrics to fix it.
ByteDance · Maoqi Liu, Junwei He, Bowen Zhang +5
#161 ▲72 ★13 ❝0 2026-09-27
TraceDance automatically builds targeted benchmarks for specific undesirable agent behaviours from real deployment traces.
ByteDance · Dehai Min, Daoan Zhang, Yiming Zeng +13
AgentsBenchmarks & dataSafety & interpretability arXiv Code HF
#162 ▲72 ★21 ❝1 2026-10-08
A multi-agent egocentric world model that generates synchronised first-person streams of agents interacting in a shared world.
KAIST AI · Dahyun Chung, Siyoon Jin, Hyunwook Choi +5
#163 ▲93 ★29 ❝0 2026-09-29
SAKI routes distillation supervision using KL-constrained teacher-guided rollouts and maximal coupling to help weak students.
meituan · Miteto Wei, Xiaohan Wang, Zehao Chen +7
#164 ▲66 ★89 ❝0 2026-09-23
Examines memory for autoregressive video generation: keeping identities, states and causal changes within bounded context.
Affiliation unverified · Harold Haodong Chen, Rongjin Guo, Disen Lan +22
#165 ▲98 ❝1 2026-10-01
ProWAM predicts actions plus an ordered sequence of sparse visual subgoals, guiding long-horizon control more efficiently than full video.
Meta · Fei Zhang, Zhaochong An, Duncan Frost +5
Robotics & embodied AIEfficient training & inference arXiv HF
#166 ▲21 ★619 ❝1 2026-10-04
Prism is dynamic sparse attention that focuses on sound-producing regions for training native 2K joint video-audio models.
Tencent Hunyuan · Shuyuan Tu, Qi Tian, Yinming Huang +8
Visual generationEfficient training & inference arXiv Code HF
#167 ▲75 ★46 ❝0 2026-09-29
EngiWorld has 1,301 expert tasks across six engineering domains (CAD, CAE, EDA…) and 26 professional software platforms.
Zhiman AI · Hongcheng Gao, Hailong Qu, Yu Lei +19
#168 ▲38 ★625 ❝0 2026-09-29
HelixWorld is a real-time interactive world model where visuals and spatial stereo sound co-evolve with user input.
NoizAI · Lei Ke, Jiahao Pan, Zeyue Tian +13
#169 ▲118 ★5 ❝0 2026-10-13
CarryOn organises long-horizon agent context around reusable task objects instead of reprocessing history.
McAuley-Lab · Yuchen Lu, Julian McAuley, Lei Zhang
#170 ▲29 ★28 ❝12 2026-09-24
Tests whether Jev, a calibrated decision model, can zero-shot detect ten alignment failures such as sycophancy, jailbreaks and deception.
Affiliation unverified · Ruoqi Guo, Yi Liu, Gelei Deng +6
#171 ▲129 ❝0 2026-09-28
LEGO-Anything has a coding agent iteratively write Blender code to reconstruct editable 3D scenes from a single image.
Amazon Web Services · Xirui Li, Peng Shi, Mingwen Dong +7
#172 ▲55 ★33 ❝1 2026-10-09
OpenMobile-2 releases environments spanning 110+ apps and ~12K trajectories to train a near-frontier, fully open mobile agent.
Nanjing University · Chenyang Yan, Yingying Zhang, Kanzhi Cheng +21
#173 ▲57 ★19 ❝0 2026-09-16
RayOrch is a distributed dataflow engine for foundation-model data prep that preserves lineage while batching efficiently.
Peking University · Xiaochen Ma, Zimo Meng, Junzhu Liang +13
#174 ▲95 ❝1 2026-09-26
GAGAR redistributes advantages by implementation quality in code-agent RL, rewarding cleaner, targeted changes.
Xiaomi MiMo · Jinhao Dong, Liang Zhao, Zihao Yue +7
#175 ▲110 ★6 ❝0 2026-10-13
GreenWAM is a robotics world foundation model using a shared joint action space across 20 robot families, serving as both world model and policy.
Sber Robotics Center · Gennady Sidorov, Valerii Kornilov, Denis Grankin +2
#176 ▲65 ★5 ❝3 2026-09-30
Finds JEV-like direct-decision models under-use ordinal scales, over-predicting middle labels.
Jilin University · Tianxiang Gao, Jinzhe Li, Zhiyuan Li +2
#177 ▲49 ★54 ❝1 2026-09-29
EVO-WAM adapts world-action models to new tasks by learning from their own verified generated video-action trajectories.
Harbin Institute of Techonology, Shenzhen · Shiyang Zhou, Xionghao Wu, Wenbo Li +11
#178 ▲37 ★86 ❝0 2026-10-14
DeltaStreamer mimics human observation with change-aware memory and query-driven replay for streaming video understanding.
ByteDance · Boyuan Sun, Deshui Miao, Wenzhao Gao +8
#179 ▲46 ★46 ❝0 2026-10-05
MC-Sparse is training-free sparse attention that selects individual KV tokens with cached compensation, closing the dense-sparse gap in DiTs.
Tencent Hunyuan · Jiarui Chen, Zeqiang Lai, Jiangshan Wang +5
Visual generationEfficient training & inference arXiv Code HF
#180 ▲51 ★112 ❝0 2026-09-30
Asks whether learning protein folding teaches LLMs reusable spatial and structural reasoning.
Shanghai JiaoTong University · Yong Liu, Zhanpeng Shi, Yizhou Dang +4
#181 ▲182 ❝0 2026-10-20
Matrix-Game 4.0 separates game logic (engine plus coding agent) from visuals (autoregressive video renderer), reaching playable 60 FPS on one RTX 5090.
Affiliation unverified · Jihai Zhang, Runjia Qian, Kaiqin Kong +15
#182 ▲103 ★7 ❝0 2026-09-26
HeteroFold transfers KV caches across different model families, avoiding repeated prefill in heterogeneous multi-agent systems.
University of Southern California · Vincent-Daniel Yun, Woosang Lim, Haneul Yoo +3
#183 ▲75 ★27 ❝0 2026-09-29
EVOKE elicits world knowledge already learned in pretraining so LLM agents transfer better to unseen environments.
Shanghai Jiao Tong University · Yuhan Guo, Jinming Liu, Liang Xu +8
#184 ▲81 ★30 ❝0 2026-09-26
DoSA uses bounds to reject keys early, speeding up sparse attention without changing exact Top-K selection.
dots studio · Fanxu Meng, Taosong Fang
#185 ▲87 ★5 ❝1 2026-09-28
Exposes each skill policy's structural prior to the agent so few-shot robots generalise both compositionally and per skill.
National University of Singapore · Puming Jiang, Tianrun Hu, Haozhe Du +4
#186 ▲94 ★12 ❝0 2026-10-20
S-Agent 2.0 equips a general coding agent with command-line 3D perception tools and scene memory, lifting spatial-reasoning benchmarks.
Ropedia · Rui Gong, Ruoyu Wang, Yalun Dai +9
#187 ▲90 ❝1 2026-09-25
Duplex-MPE uses 2,000 multi-party scenarios to test when a full-duplex voice assistant should answer, stay silent or stop.
Peking University · Chengqian Ma, Wenhao Feng, Weixuan Jin +7
#188 ▲63 ★11 ❝0 2026-10-01
AutoGUIWorld uses image generators as visual world models of GUIs to synthesise diverse interaction trajectories.
Tencent Hunyuan · Cheng Yang, Yifan Wu, Yutao Huang +18
#189 ▲23 ★2.9k ❝0 2026-10-05
RealtimeWAM generates actions in one step with asynchronous inference to make world-action models real-time.
Nanyang Technological University · Chengtao Lv, Jinyang Du, Shuyi Feng +7
Robotics & embodied AIEfficient training & inference arXiv Code HF
#190 ▲175 ❝0 2026-10-15
Trains VLMs with RL to reason and actively move their viewpoint in 3D, seeing one image at a time like a human.
University of California at San Diego · Yijiang Li, Bingyang Wang, Nuno Vasconcelos
#191 ▲56 ★12 ❝2 2026-09-21
A script-aware mixture-of-experts gives one multilingual scene-text recogniser that is simpler than per-language models and lighter than VLMs.
Fudan University · Xingsong Ye, Yongkun Du, Jiaxin Zhang +6
#192 ▲86 ★20 ❝0 2026-09-28
Proposes general asynchronous agents that accept new inputs while thinking or acting, covering voice, embodied and monitoring settings.
Yandex Research · George Yakushev, Denis Mazur, Vladimir Bartenev +4
#193 ▲47 ★164 ❝0 2026-10-01
SciUtopia simulates academic ecosystems with LLM agents: topic choice, collaboration, review, citation and funding.
Georgia Institute of Technology · Yiqiao Jin, Yiyang Wang, Lucheng Fu +8
#194 ▲45 ★28 ❝0 2026-10-16
Microsoft's Self-HPO alternately evolves a coding agent's harness and policy model for recursive self-improvement.
Microsoft Research · Zhepei Wei, Wenlin Yao, Baolin Peng +5
#195 ▲41 ★233 ❝0 2026-10-06
WorldSonus adds real-time, spatially aligned stereo sound to world models with mid-stream sound control.
NoizAI · Pengjun Fang, Jingyi Fa, Kam Man Wu +9
#196 ▲108 ❝0 2026-09-28
Finds chunked KV-cache compression causes phase sensitivity: retrieval accuracy varies with position relative to window boundaries.
ByteDance Seed · Xingyu Zhu, Pu, Yi +6
#197 ▲82 ★13 ❝0 2026-10-14
LatentLoop finds loop visits in looped MoE play asymmetric roles and allocates compute asymmetrically for better results.
Affiliation unverified · Zefeng He, Yunkai Chai, Xiaoyang Chen +5
#198 ▲57 ★17 ❝0 2026-09-29
Studies when visual generation training improves understanding, finding image-to-image training helps under the right recipe.
UC Berkeley · Jiaxin Ge, Yiming Qin, Ji Xie +13
#199 ▲84 ★10 ❝0 2026-10-14
Speculative Sampling for interactive video generation caches predictions from large windows to get large-chunk quality at small-chunk latency.
university of science and technology of china · Yubo Huang, Yuxuan Zhang, Jiaming Liu +2
Visual generationEfficient training & inference arXiv Code HF
#200 ▲106 ★4 ❝0 2026-09-30
WorldAuditBench has multimodal agents navigate 3D worlds to find anomalies like floating objects or walk-through walls.
University of California, Santa Barbara · Ziyan Jiang, Jingbo Yang, Jiabao Ji +5
#201 ▲35 ★49 ❝3 2026-10-05
Driving looped language models towards fixed points enables truncated backprop, KV sharing and cheaper RL with little accuracy loss.
Institute of Foundation Models · Benhao Huang, Chufan Shi, Junlin Chen +4
#202 ▲63 ★14 ❝1 2026-09-30
SciSlopBench collects 390 AI-generated papers to detect plausible-looking but broken 'scientific slop' and explores mitigations.
Seoul National University · Yerim Oh, Young-Jun Lee, Jaewoo Ahn +2
#203 ▲37 ★67 ❝0 2026-10-09
Trains a corrector that refines the denoiser's prediction at each step to reduce exposure bias, improving DiT, SiT and JiT samples.
University of California, Berkeley · Donghoon Ahn, Runqian Wang, Alexei A. Efros +2
#204 ▲74 ★17 ❝0 2026-10-09
EmbodiedCLBench is the first embodied continual-learning benchmark, testing whether agents recombine learned skills on new tasks.
PKU-VaLuE-Lab · Jie Huang, Yanan Chen, Ruixun Liu +6
#205 ▲64 ★18 ❝0 2026-09-29
Clearly defines what robot in-context learning should follow and offers a minimalist, reproducible recipe for manipulation.
Affiliation unverified · Minxing Li, Minghao Han, Weizhi Zhao +10
#206 ▲74 ★23 ❝0 2026-09-28
Technical report for LongCat-DeepResearch, a multi-agent workflow that plans, researches in parallel and revises evidence-grounded reports.
LongCat · Meituan LongCat Team, He Zhu, Yue Xu +28
#207 ▲62 ★36 ❝0 2026-10-15
Mosaic generalises agentic RL to multi-session trajectories, matching inference-time context compaction and sub-agent forking.
LARK Lab@HKUST (GZ) · Yilong Xu, Minrui Xu, Xinyu Zhou +3
#208 ▲103 ❝0 2026-09-29
Proposes 'predictive credit' to measure whether research agents' explanations improve experimental forecasts; preregistered tests were inconclusive.
Carnegie Mellon University · Jingjie Ning, Xueqi Li, Yibo Kong +1
#209 ▲145 ❝0 2026-10-05
VepAgent combines causal-transition reasoning with tool-augmented RL for video event prediction.
UCSC-VLAA · Qiutong Chen, Yuchan Guo, Zhenlong Yuan +10
#210 ▲62 ★27 ❝0 2026-10-16
Scene-Designer learns design intelligence from design and critique experience to generate coherent 3D indoor scenes from text.
ZJU-OmniAI · Xuanyu Liu, Hongyan Feng, Miao Pan +5
#211 ▲24 ★1.1k ❝0 2026-10-12
StartLux-Decision models (0.8B–27B) answer confident cases directly and reason only when uncertain, with RL that rewards calibrated decision probabilities.
StartLux · Xialie Zhuang, Zunhai Su, Jia Pan +3
#212 ▲34 ★111 ❝1 2026-09-24
Qwen-Planner-Agent uses a closed-loop AI-for-AI framework to iteratively build real-world mobile planner agents.
Tongyi-MAI · Tingyu Qu, Weigao Sun, Yuecheng Liu +23
#213 ▲104 ❝1 2026-09-21
RULER uses instance-aware multi-axis rubrics as rewards for SVG generation, reducing the reward hacking seen with scalar metrics.
inclusionAI · Hangyu Ran, Yuhao Zheng, Yingying Zhang +2
#214 ▲148 ❝0 2026-10-20
PAR aligns each loop iteration of a looped LM with task progress and anchors state norms, extrapolating state tracking to 16x training length.
ant-international · Pan Wang, Yihao Hu, Guangyuan Dong +8
#215 ▲72 ★2 ❝2 2026-10-06
CheckerBench tests whether long-horizon agents can build working static-analysis checkers, with 300 tasks from 297 CVEs.
Humanlaya Data Lab · Hang He, Li Wang, Hao Chen +9
#216 ▲62 ★30 ❝0 2026-10-04
Memadapter uses counterfactual adaptation to reduce memory-induced sycophancy, which arises even from correct memories.
DEEP Group at Jilin University · Ruqing Ning, Haibo Meng, Zhishang Xiang +4
#217 ▲58 ★38 ❝0 2026-10-12
AReA adapts the attention receptive field across denoising steps so diffusion transformers generate beyond-training resolutions more cheaply.
University of Toronto Computer Science · Javad Rajabi, Koorosh Roohi, David B. Lindell +1
Visual generationEfficient training & inference arXiv Code HF
#218 ▲55 ★37 ❝0 2026-10-14
A survey of multimodal agent memory, from perceiving and maintaining memories to learned memory-management policies.
Fudan University · Minghao Guo, Qingyue Jiao, Xiujin Liu +77
#219 ▲40 ★153 ❝0 2026-09-29
TERRA retargets motion with terrain to musculoskeletal models so muscle-driven agents can walk on complex ground.
Mathis Group @ EPFL · Merkourios Simos, Chengkun Li, Bianca Ziliotto +1
#220 ▲91 ★4 ❝0 2026-10-14
CriticOPD has the teacher critique wrong student rollouts before rewriting, restoring reliable supervision in on-policy distillation.
Affiliation unverified · Kaixiang Zhao, Tianrun Yu, Shangzhe Li +4
#221 ▲46 ★72 ❝0 2026-09-27
Finds retrieved history mainly helps a personal GUI agent's first step, and proposes activating experience only when it applies.
Nanyang Technological University · Fuyao Zhang, Xuan Wang, Zherui Li +3
#222 ▲101 ❝0 2026-09-29
Microsoft builds an entity-based corpus map so search agents can follow evidence across documents instead of rediscovering links.
Microsoft · Soyeong Jeong, Sujay Kumar Jauhar, Sung Ju Hwang +1
#223 ▲43 ★111 ❝0 2026-10-14
A survey of agentic robots organised around model, data, environment and harness.
Affiliation unverified · Chonghan Qin, Dongming Wu, Kaituo Feng +13
#224 ▲25 ★185 ❝0 2026-10-14
Qwen's BlenderWorld benchmarks visual agents creating and editing 3D content in Blender from real-world references.
Qwen · Xinyu Fang, Yuchi Wang, Weihao Yu +12
#225 ▲107 ❝1 2026-10-01
SALD lets a diffusion model score each image-caption pair at two noise levels, yielding self-referenced training signals without a teacher.
Indian Institute of Technology, Kanpur · Aryan Das, Surjo Dey, Koushik Biswas +4
#226 ▲64 ★22 ❝0 2026-10-15
VLA-Δ explicitly supervises physical state transitions to reduce VLA overfitting to observation-action pairs.
ZJU-OmniAI · Qi Lu, Jiarun Li, Ce Zhang +5
#227 ▲68 ★14 ❝0 2026-09-30
StereoBind ties stereo sound position to on-screen source motion for immersive joint video-audio generation.
Affiliation unverified · Hanmo Chen, Chengcheng Liu, Tianxiao Chen +7
#228 ▲75 ★11 ❝0 2026-09-30
EgoTools targets tool-centric reasoning in real egocentric videos, covering hand-tool-object relations and procedures.
Ropedia · Shulin Tian, Junsu Kim, Shuai Liu +17
#229 ▲80 ★2 ❝1 2026-09-26
X-Tree tokenises recurring sub-procedures in agent trajectories and trains on that hierarchy, improving generalisation without LLM calls.
University of Waterloo · Sitao Cheng, Xunjian Yin, Zhiyuan Sun +4
#230 ▲50 ★37 ❝0 2026-10-09
Multi-Stream Attention Residuals extend depth-wise attention residuals to multiple heads, with sizeable gains at little extra cost.
Shanghai Jiao Tong University · Xiaohan Qin, Xiangdong Zhang, Tuo Dai +7
#231 ▲41 ★123 ❝0 2026-10-13
FlashVSR+ speeds up one-step video super-resolution with hybrid attention and aligns it to human preference via reward-weighted distribution matching.
MMLab-CUHK · Ruchang Yao, Shi Guo, Junhao Zhuang +7
Visual generationEfficient training & inference arXiv Code HF
#232 ▲25 ★826 ❝0 2026-10-15
Intern-Decision (0.8B–4B) returns structured choices with probabilities instead of free text, making agent decisions faster.
Intern Large Models · Tong Zhu, Zhe Xu, Zefeng He +7
MultimodalAgentsEfficient training & inference arXiv Code HF
#233 ▲66 ★5 ❝1 2026-09-25
DMM refines joint actions in decentralised multi-agent pathfinding by iterative intent denoising, avoiding incompatible combinations.
Affiliation unverified · Valeriy Vyaltsev, Anton Andreychuk, Taisia Zlotnikova +3
#234 ▲40 ★41 ❝1 2026-10-07
RobotWorld uses 84 simulated tasks (manipulation, locomotion, driving, aerial) to test multimodal agents at robot use.
Affiliation unverified · Zhiqin Yang, Chenxin Li, Xiaomeng Hu +30
#235 ▲91 ❝0 2026-10-06
Qwen's TRACE aligns the training and rollout FP4 quantisation paths for low-precision RL of MoE language models.
Qwen · Xin Wang, Hao Yu, Zhengyang Zhuge +9
Efficient training & inferenceReinforcement learningLLMs arXiv HF
#236 ▲27 ★187 ❝1 2026-10-06
KLPO anchors the KL regulariser at the sampling policy to handle stale, mismatched rollouts in asynchronous LLM-agent RL.
math-ai · Yifan Zhang
#237 ▲31 ★26 ❝1 2026-09-24
Tencent Hunyuan's ExplorationBench measures scientific exploration in verifiable alien worlds, ruling out recall from pre-training.
Tencent Hunyuan · Ming Zhang, Zhenghao Xiang, Peizhong Gao +17
#238 ▲85 ★5 ❝0 2026-10-06
DecepEval uses 1,532 instances and a 'deception diamond' framework to test when LLM agents are likely to deceive.
Xi'an Jiaotong University · Yiming Xu, Hongyue Yu, Beihua Yang +8
Safety & interpretabilityBenchmarks & dataAgents arXiv Code HF
#239 ▲85 ★4 ❝0 2026-10-13
WorkRover scales RL for long-horizon cowork agents by recursively evolving tasks, work contexts and verifiers.
Nex AGI · Hang He, Linting Wang, Guanming Liu +14
#240 ▲41 ★14 ❝0 2026-10-15
Tsinghua's AutoSFT gives an agent a full data action space—mix, prune, repair, synthesise—to automate SFT data research.
Tsinghua NLP Group · Bingxiang He, Pengqi Sun, Shihao Peng +18
#241 ▲88 ❝0 2026-10-02
NAVA-WAM pretrains the action policy directly from observation-only videos, reducing reliance on action-labelled robot data.
Meta · Zhaochong An, Fei Zhang, Menglin Jia +10
#242 ▲80 ★6 2026-10-19
SpecMRL reorganises features on a parameter-derived spectral basis so Matryoshka prefixes carry the most important information.
Affiliation unverified · Zhongxin Chen, Songhao Wu, Heng Cui +3
#243 ▲53 ❝2 2026-09-29
Google's AIM manages, selects and explores research ideas for automated research, inspired by Bayesian optimisation.
Google · Hyeong Kyu Choi, Bhavana Dalvi Mishra, Jiefeng Chen +7
#244 ▲86 ★4 ❝0 2026-10-15
SCOPE, a GRPO-based objective, credits semantic spans rather than sub-word tokens when training prompt rewriters for text-to-image.
University of Rochester · Yufei Jiao, Jinfa Huang, Zeyue Xue +5
#245 ▲55 ★28 ❝0 2026-10-04
EVISKILL grounds agent skill evolution in replayable evidence to judge which edits should persist.
DEEP Group at Jilin University · Yan Zhou, Yili Wang, Yiwei Dai +2
#246 ▲86 ❝0 2026-10-01
Microsoft's ActiveSaddler adapts the training curriculum alongside the evolving agent harness for automated harness optimisation.
Microsoft · Sungho Park, Wonjoong Kim, Jue Zhang +8
#247 ▲123 ❝0 2026-09-30
GraphForge synthesises verifiable workspace tasks grounded in real files via evidence graphs to train working agents.
University of Science and Technology of China · Qisheng Su, Hanchen Wang, Guanru Zhu +10
#248 ▲45 ★45 ❝0 2026-10-16
Xiaomi-Lens-0 is a 4B MLLM on Qwen3.5 that predicts segmentation masks from its own visual representations.
SeerRay-Lab · Pei Fu, Yike Liu, Yue Sun +13
#249 ▲56 ★21 ❝0 2026-10-01
SimuVerity's 101 tasks check whether agent-generated Simulink models meet engineering requirements, not just whether they run.
Xi'an Jiaotong University · Ruiqi Zhang, Jiahao Wang, Mingxuan Li +9
#250 ▲52 ★34 ❝0 2026-10-09
Work2Skill captures human GUI demonstrations and induces reusable skills for computer-use agents.
Nex AGI · Yuqi Huang, Hui Li, Yifei Cao +9
#251 ▲60 ★24 ❝0 2026-10-01
Uses MLLM spatial understanding to manage long-term memory so world models stay spatially consistent in long video generation.
Affiliation unverified · Ying Yang, Guiyu Zhang, Lianghua Huang +5
#252 ▲49 ★41 ❝0 2026-10-07
Tetris3D conditions each object on its neighbours' geometry and physical relations so single-image 3D scenes fit together.
KAIST AI · Jaeyeong Kim, Jinhyuk Jang, Jongmin Lee +2
#253 ▲50 ★31 ❝0 2026-09-28
Interleaved RL jointly trains reflection text and image generation so unified models can diagnose and repair their own images.
MMLab@NTU · Yijia Fan, Ziqi Huang, Zhongang Cai +5
MultimodalReinforcement learningVisual generation arXiv Code HF
#254 ▲53 ★4 ❝0 2026-10-15
PhysClosureBench uses 50 expert-verified physics tasks to test whether agents can run investigations to well-supported conclusions.
Shanghai AI Laboratory · Yijia Mao, Song Dai, Tao Chen +14
#255 ▲68 ★10 ❝0 2026-09-29
E-MoE improves non-factorised diffusion language models with enhanced mixture-of-experts, raising few-step quality without posterior collapse.
Affiliation unverified · Arseny Ivanov, Alexander Kolesov, Alexander Korotin +2
#256 ▲35 ★37 ❝0 2026-09-27
Tsinghua's Diffusion Reward Model recasts reward modelling as conditional density estimation to capture multimodal human preferences.
Tsinghua NLP Group · Xiangyang Wang, Bingxiang He, Zeyuan Liu +13
#257 ▲65 ★12 ❝0 2026-09-28
PDE-JEPA learns latent dynamics of parametric PDEs with predictive (JEPA-style) pretraining instead of reconstruction.
Zhejiang University · Zhentao Tan, Jianrong Zhang, Ruijie Quan +1
#258 ▲39 ★28 ❝1 2026-10-01
Stability AI's 4Director controls camera and object motion in a video world model via explicit rigid meshes and per-frame transforms.
Stability AI · Wei Cao, Hao Zhang, Vikram Voleti +5
#259 ▲79 ★3 ❝0 2026-10-13
ReMaRk scores recommendation lists against the union of all replies, removing responder noise from GRPO training of LLM recommenders.
Nanyang Technological University · Xin Li, Hao Jiang, Jinghao Guo +2
#260 ▲45 ★19 ❝1 2026-10-07
RLHND uses a video foundation model to estimate hand pose and touch from egocentric video, making human videos more useful for robots.
RLWRLD · Seungjun Moon, Subin Jeon, Sangwoo Kim +2
#261 ▲31 ★194 ❝0 2026-10-07
Iris-3B pretrains and converts pixel-space diffusion models to test whether skipping the VAE helps detail-sensitive tasks.
speridlabs · Hanqiu Li Cai, Chema Garabito
#262 ▲79 ❝0 2026-10-12
X-Ragent uses tool-augmented RL for chest X-ray reasoning, learning when to call auxiliary evidence and when to ignore it.
Carnegie Mellon University · Yi Wang, Zhenlong Yuan, Yuchan Guo +9
#263 ▲30 ★11 ❝1 2026-10-06
Stanford's Stateless Language Agents keep research state outside the agent, tackling duplication and stalls in long-horizon automated research.
Stanford University · Qizheng Zhang, Changxiu Ji, Isaac Sun +15
#264 ▲60 ★26 ❝0 2026-10-01
EditHero is a benchmark for long-horizon, part-level 3D editing, checking that each revision changes only what was asked.
Affiliation unverified · Ruihan Yu, Yu-Ju Tsai, Muyao Niu +9
#265 ▲33 ★16 ❝0 2026-10-09
Studies which visual representations actually help pixel diffusion transformers, finding better understanding does not imply better generation.
alibaba · Zihao Pan, Mengting Chen, Cheng Shi +6
#266 ▲54 ★11 ❝0 2026-10-06
U-Space analyses when and why uncertainty arises in language models, to help judge whether an individual answer can be trusted.
Multimodal AI Lab - Technical University of Darmstadt · Tobias Braun, Nils Loose, Alexander Herzog +4
#267 ▲115 ❝0 2026-09-29
MotorMind scaffolds general vision-language models for zero-shot robot manipulation without specialised VLA training.
University of Illinois at Urbana-Champaign · Bingxuan Li, Siqi Song, Yizhuo Wu +3
#268 ▲73 ❝0 2026-09-21
VideoGen-Agent trains a multimodal agent with multitask agentic RL to use tools for knowledge- and identity-heavy video prompts.
Princeton University · Binxu Li, Haoyi Duan, Yuhui Zhang +9
#269 ▲73 ❝0 2026-10-14
Cortex consolidates gains from context into parametric memory, keeping them after the context is removed.
ByteDance Seed · Jintian Zhang, Feng He, Xinnian Liang +5
#270 ▲112 2026-10-19
Collective experience learning lets 96 deployed robots share execution data, retrieving successful segments for failures to fine-tune a common policy without new demos.
Affiliation unverified · Chao Yu, Shu'ang Yu, Hao Lin +41
#271 ▲68 ★5 ❝0 2026-10-18
CoEvo-RSI tackles the brain–body mismatch when models and agent harnesses co-evolve, using a meta-agent to coordinate harness evolution and checkpoint choice.
Affiliation unverified · Jiaqi Su, Guibin Zhang, Jie-Jing Shao +5
#272 ▲38 ★10 ❝0 2026-10-01
SSR has small models select from predefined reasoning candidates instead of free generation, cutting cost for multimodal search agents.
Carnegie Mellon University · Feiyu Gavin Zhu, Xiaoyu Zhu, Jiqi Yang +9
#273 ▲60 ★9 ❝0 2026-10-18
VLA-Rolling reuses the unexecuted action tail as the starting point for denoising, cutting steps for frozen flow-matching VLAs while often raising success.
ZJU-OmniAI · Sicheng He, Yi Pan, Qiuting Yu +10
Robotics & embodied AIEfficient training & inference arXiv Code HF
#274 ▲46 ★22 ❝0 2026-10-10
BridgeWAM links video and action experts through 32 latent bridge queries instead of dense layer-wise coupling, enabling a two-layer action head.
Fudan University · Jiaxin Fang, Ruitong Liu, Zeyu Lai +6
#275 ▲34 ★14 ❝0 2026-10-15
A controlled probe shows unified multimodal models can transfer knowledge learned through image generation into text answers, though unevenly.
Z.ai · Wenkai Li, Wenyi Hong, Zhuoyi Yang +1
#276 ▲69 ❝1 2026-09-30
PhysVista evaluates VLMs' physical intelligence through a perception-reasoning-assessment loop.
university of science and technology of china · Xinge Peng, Yiting Lu, Tianwu Zhi +4
#277 ▲29 ★19 ❝0 2026-10-13
Open-o3-Video-v2 actively gathers more frames and writes timestamps and boxes into its reasoning as verifiable evidence.
Peking University · Jiahao Meng, Zhongyuan Bao, Yue Tan +7
#278 ▲55 ★6 ❝0 2026-10-15
Lexical reference frames read hidden states through the model's own remaining layers, giving far more faithful readings than fixed lenses.
Affiliation unverified · Jian Gu, Hongyu Zhang, Chunyang Chen +1
#279 ▲85 ❝0 2026-10-03
Analyses why self-evolving reasoning models collapse (invalid and repeated questions) and proposes question-quality controls.
Huang's INTelligence lab · Jinyuan Li, Chengsong Huang, Langlin Huang +4
#280 ▲42 ★17 ❝0 2026-10-20
VPM is a world model that jointly forecasts multi-view future video and 3D point trajectories, extended to robot control.
Affiliation unverified · Byungwoo Jeon, Sunghwan Hong, Dohyeon Kim +10
#281 ▲42 ★12 ❝0 2026-10-18
CoworkEnv synthesizes executable training environments for AI coworker agents, supporting SFT and RL of compact models.
Affiliation unverified · Zhongwei Xie, Yiming Du, Jiaxin Bai +10
#282 ▲32 ★43 ❝0 2026-10-16
DLite is history-free speculative decoding that drafts locally from the target model's hidden states, suited to ever-growing agent contexts.
Shanghai Jiao Tong University · Jiaming Xu, Hanzhen Wang, Tianlang Zhao +7
#283 ▲35 ★29 ❝0 2026-10-16
RAP pairs 25K+ papers with posters derendered into HTML/CSS slots, enabling render-and-compare evaluation of paper-to-poster generation.
meituan · Haonan Han, Yukang Lin, Minliang Lin +7
#284 ▲52 ❝0 2026-10-16
TreeOPSD builds a tree over agent turns, backs up terminal rewards into turn-level credit and self-distills without a critic for long-horizon agent RL.
Tencent Hunyuan · Heming Zou, Qi Wang, Yixiu Mao +7
#285 ▲37 ★22 2026-10-18
MT Forcing trains autoregressive-diffusion editors with a single-turn distillation teacher and teacher-forcing guidance to curb multi-turn editing drift.
SenseNova · Houyuan Chen, Fanzhou Wang, Xiangyu Fan +10
#286 ▲27 ★8 2026-10-19
RoAR-VAE trains tokenizers so semantics and pixels remain recoverable from corrupted latents, making latents easier for diffusion models to learn.
Tsinghua-LeapLab · Yang Yue, Fangyun Wei, Yitong Wang +4
#287 ▲26 ★47 ❝0 2026-10-19
Manga2Animate uses paired creator and reviewer agents to plan scripts and storyboards before generating animation faithful to the source manga.
National Yang Ming Chiao Tung University · Sheng-Wei Zhang, Hsi-An Chen, Yan-Ting Liou +3
#288 ▲33 ★12 ❝0 2026-10-16
MIST separates instruction execution from memory in video world model tests, finding the bottleneck is usually execution rather than forgetting.
The University of Hong Kong · Weiyang Jin, Jiwen Yu, Sihan Xu +2
#289 ▲26 ★31 ❝0 2026-10-19
InfiniDream has a VLM drive procedural algorithms to generate open-ended, editable photorealistic 3D assets and large worlds.
Alaya Lab · Yi-Chuan Huang, Hao-Jen Chien, Zheng-Hui Huang +3
#290 ▲37 ★7 2026-10-19
AnyGoal benchmarks whether world models generalize to recombinations of familiar state and action factors; current models consistently fail.
galilai-group · Heejeong Nam, Divyat Mahajan, Quentin Le Lidec +2
#291 ▲24 ★11 ❝0 2026-10-20
MMEnterprise-Bench has 1,613 questions over evolving multimodal workplace records, testing evidence reasoning, conflict resolution and unanswerability.
Affiliation unverified · Seohyun Lee, Jongha Kim, Dohwan Ko +4
#292 ▲47 ❝0 2026-10-02
Finds 12 agent models systematically favour items from certain sources when shopping, booking or citing, and proposes mitigations.
Seoul National University · Jonghyun Song, Haewon Park, Jeonghoon Shim +2
#293 ▲28 ★6 ❝0 2026-10-05
MemPilot trains an RL policy to curate multimodal agent memory on demand under performance–cost–latency preferences.
Nanyang Technological University · Haozhen Zhang, Haodong Yue, Quanyu Long +6
#294 ▲27 ★4 ❝0 2026-10-19
HarnessPro evolves agent harnesses without ground-truth tests, returning lite, balanced and heavy variants that trade performance against cost.
Affiliation unverified · Zhuoshi Pan, ZhiYuan Feng, Yukuo Cen +6
#295 ▲27 ❝0 2026-10-19
SWIFT extrapolates training targets away from a frozen weak denoiser to boost a stronger diffusion model with no extra inference cost.
alibaba · Yanjin He, Cuifeng Shen, Wanzhou Lei +5
#296 ▲28 ★3 ❝0 2026-10-19
AdaExploreBench uses hidden, silently drifting rules to test whether LLM agents proactively explore and adapt at test time.
HKUST · Rui Wang, Zishen Lai, Jiayu Liu +15
#297 ▲22 ★9 ❝0 2026-10-06
A data-free, simulation-free diffusion distillation where one student both generates and estimates scores, reaching strong one-step FID.
Vector Institute · Yuxiang Fu, Qi Yan, Zike Wu +4
Visual generationEfficient training & inference arXiv Code HF
#298 ▲26 ★4 ❝0 2026-10-09
APEX-Harm tests finance, consulting and legal agents against prompt and script injection in large shared workspaces.
King Abdullah University of Science and Technology · Ziyi Yang, Adel Bibi, Guohao Li +2
Safety & interpretabilityAgentsBenchmarks & data arXiv Code HF
#299 ▲24 ★4 ❝0 2026-10-05
Has an LLM agent rewrite molecular geometry optimisers, discovering algorithms needing fewer force calls than the fastest open baseline.
Affiliation unverified · Artem Tsypin, Vladimir Deshchenya, Kuzma Khrabrov +4
#300 ▲21 ★9 ❝0 2026-09-24
IndicBankBench evaluates Indian retail-banking assistants on 799 cases across safety, tool use and answer quality.
National Payments Corporation of India · Suvradip Paul, Chandra Bhushan, Harsh Sharma +4
#301 ▲34 ❝0 2026-10-14
Interlock represents tasks as typed completion graphs to synthesize long-horizon agent tasks and rubrics that check end-to-end completion.
LongCat · Linji Hao, Yanji He, Zihan Wang +6
#302 ▲22 ❝0 2026-10-20
Co-generates video, replayable 3D motion for any rig and a registering camera, turning video-model motion into usable 3D animation.
NVIDIA · Noam Rotstein, Yoad Tewel, Chen Tessler +5
#303 ▲33 ❝0 2026-10-16
MTEdit builds 500K multi-turn image-editing trajectories by generating several edit states in one packed canvas, plus a benchmark.
SenseNova · Houyuan Chen, Fanzhou Wang, Xiangyu Fan +8
#304 ▲28 2026-10-19
KronLSTM introduces a Kronecker delta rule that revises matrix memory along one direction, giving stable long-context linear attention that often beats DeltaNet.
NX-AI · Anamaria-Roberta Hartl, Levente Zólyomi, Michael List +3
#305 ▲26 ❝0 2026-10-03
Argues real-world super-resolution works best in a frozen vision-foundation feature space rather than reconstruction latents or pixels.
RTP-LLM · Wanzhou Lei, Cuifeng Shen, Yanjin He +6
#306 ▲23 ❝0 2026-09-24
Builds taxonomies of where retrieval-based factuality checking of long medical answers fails.
Center for Language and Speech Processing @ JHU · Heyuan Huang, Jirui Dai, Alexandra DeLucia +5
#307 ▲22 2026-10-19
SpecKCast forecasts DiT outputs in the frequency domain with Kalman filters, running the model only when uncertainty is high, for training-free speedup.
Samsung Research · Javad Rajabi, Hakki Can Karaimer, David B. Lindell +2
No papers match — try loosening the filters
Data updated: Latest AI papers(UTC+8)