TOPIC · AGENT · 122 PAPERS
LLMsReasoningAlignmentAgentsMultimodalVisual generationVision & 3DRobotics & embodied AIEfficient training & inferenceSafety & interpretabilityAI for ScienceCode & SWEBenchmarks & dataReinforcement learning
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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.
Data Science & Artificial Intelligence Lab at HKUST · Peisong Wang, Feixue Liu, Yize Meng +16
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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 +9
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
#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
▲138 ❝2 2026-09-18
CodeMidas turns implemented functionality in codebases into executable coding RL environments using only source code.
Xiaomi MiMo · Bowen Ye, Lei Li, Shicheng Li +16
▲81 ★108 ❝1 2026-09-18
RecreationWorld asks computer-use agents to observe running software and re-implement it, with verifiable environments on five platforms.
Qwen · Shuai Bai, Jiayong Deng, Sicheng Fan +30
▲152 ★994 ❝3 2026-09-14
EvoOntology provides data agents with a self-evolving ontology layer served over MCP to bridge the gap to heterogeneous data.
RUC-DataLab · Meiduo Chong, Shaolei Zhang, Ju Fan +1
Data updated: Latest AI papers(UTC+8)