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

Agents Reinforcement learning arXiv HF

#37 ▲214 ★234 ❝0 2026-10-13

Agent-Reflex: Teaching Language Agents to Act Reflectively

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

Agents Reinforcement learning arXiv Code HF

#46 ▲137 ★114 ❝0 2026-10-13

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

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 & SWE Visual generation Reinforcement learning arXiv Code HF

#47 ▲181 ★57 ❝1 2026-09-28

Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation

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 & inference Reinforcement learning arXiv Code HF

#52 ▲133 ★105 ❝0 2026-10-13

Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes

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

Agents Vision & 3D Reinforcement learning arXiv Code HF

#68 ▲189 ★10 ❝1 2026-10-06

Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight

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

Reinforcement learning Agents arXiv Code HF

#70 ▲218 ★10 ❝0 2026-10-15

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

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 learning Efficient training & inference arXiv Code HF

#86 ▲111 ★30 ❝0 2026-10-01

Sharpening Tax in Post-Training

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

Reinforcement learning Agents arXiv Code HF

#87 ▲103 ★114 ❝0 2026-09-22

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

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

Agents Reinforcement learning arXiv Code HF

#88 ▲154 ★34 ❝0 2026-10-08

Reflex: Visually Grounded Reactive Humanoid Control

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

Robotics & embodied AI Reinforcement learning arXiv Code HF

#89 ▲149 ★38 ❝0 2026-10-14

MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments

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

Agents Reinforcement learning Benchmarks & data arXiv Code HF

#90 ▲327 ❝0 2026-09-26

Scaling Properties of Same-Family On-Policy Distillation

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 & inference Reinforcement learning arXiv HF

#95 ▲134 ★39 ❝0 2026-09-29

AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks

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

Agents Reinforcement learning arXiv Code HF

#109 ▲30 ★2.1k ❝0 2026-10-06

NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale

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 & inference Reinforcement learning arXiv Code HF

#111 ▲92 ❝6 2026-10-08

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

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

LLMs Reinforcement learning Multimodal arXiv HF

#113 ▲92 ★83 ❝0 2026-10-14

More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning

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

Agents Reinforcement learning Benchmarks & data arXiv Code HF

#117 ▲105 ❝3 2026-10-02

Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

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

Agents Reinforcement learning arXiv HF

#139 ▲152 ❝0 2026-10-05

LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches

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 learning Efficient training & inference arXiv HF

#150 ▲140 ❝0 2026-09-29

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

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

Visual generation Reinforcement learning arXiv HF

#151 ▲96 ★21 ❝0 2026-10-12

TPPO: Tracking-Value PPO For Language Model Reasoning

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

Reinforcement learning Reasoning arXiv Code HF

#157 ▲50 ★45 ❝0 2026-09-20

One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents

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

Code & SWE Reinforcement learning Agents arXiv Code HF

#160 ▲68 ★22 ❝0 2026-09-30

Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics

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

Reinforcement learning Alignment AI for Science arXiv Code HF

#172 ▲55 ★33 ❝1 2026-10-09

OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools

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

Agents Reinforcement learning arXiv Code HF

#174 ▲95 ❝1 2026-09-26

Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL

GAGAR redistributes advantages by implementation quality in code-agent RL, rewarding cleaner, targeted changes.

Xiaomi MiMo · Jinhao Dong, Liang Zhao, Zihao Yue +7

Code & SWE Reinforcement learning arXiv HF

#190 ▲175 ❝0 2026-10-15

Learning to Think and Explore in 3D World

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

Multimodal Reinforcement learning Reasoning arXiv HF

#194 ▲45 ★28 ❝0 2026-10-16

Self-Evolving Coding Agents via Harness-Policy Optimization

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

Code & SWE Agents Reinforcement learning arXiv Code HF

#207 ▲62 ★36 ❝0 2026-10-15

Mosaic: Multi-Session Agentic Reinforcement Learning

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

Reinforcement learning Agents arXiv Code HF

#209 ▲145 ❝0 2026-10-05

VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction

VepAgent combines causal-transition reasoning with tool-augmented RL for video event prediction.

UCSC-VLAA · Qiutong Chen, Yuchan Guo, Zhenlong Yuan +10

Multimodal Reinforcement learning Reasoning arXiv HF

#211 ▲24 ★1.1k ❝0 2026-10-12

StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions

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

Reasoning Reinforcement learning arXiv Code HF

#212 ▲34 ★111 ❝1 2026-09-24

Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents

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

Agents Reinforcement learning arXiv Code HF

#213 ▲104 ❝1 2026-09-21

RULER: Instance-aware Rubric Rewards for SVG Generation

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

Reinforcement learning Visual generation arXiv HF

#219 ▲40 ★153 ❝0 2026-09-29

TERRA: Terrain-Aware Reconstruction, Retargeting and Control for Musculoskeletal Locomotion

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

Robotics & embodied AI Reinforcement learning arXiv Code HF

#233 ▲66 ★5 ❝1 2026-09-25

Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding

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

Robotics & embodied AI Reinforcement learning arXiv Code HF

#235 ▲91 ❝0 2026-10-06

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models

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 & inference Reinforcement learning LLMs arXiv HF

#236 ▲27 ★187 ❝1 2026-10-06

On KL-Regularized Policy Optimization

KLPO anchors the KL regulariser at the sampling policy to handle stale, mismatched rollouts in asynchronous LLM-agent RL.

math-ai · Yifan Zhang

Reinforcement learning LLMs arXiv Code HF

#239 ▲85 ★4 ❝0 2026-10-13

WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution

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

Agents Reinforcement learning arXiv Code HF

#244 ▲86 ★4 ❝0 2026-10-15

SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation

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

Reinforcement learning Visual generation arXiv Code HF

#253 ▲50 ★31 ❝0 2026-09-28

Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning

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

Multimodal Reinforcement learning Visual generation arXiv Code HF

#256 ▲35 ★37 ❝0 2026-09-27

Diffusion Reward Models

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

Alignment Reinforcement learning arXiv Code HF

#259 ▲79 ★3 ❝0 2026-10-13

Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders

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

Reinforcement learning LLMs arXiv Code HF

#262 ▲79 ❝0 2026-10-12

X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning

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

Reinforcement learning Reasoning AI for Science arXiv HF

#268 ▲73 ❝0 2026-09-21

VideoGen-Agent: Reinforcing Video Generation Agents

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

Visual generation Agents Reinforcement learning arXiv HF

#279 ▲85 ❝0 2026-10-03

Questioning the Questions: Sustaining Self-Evolution in Reasoning Models

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

Reasoning Reinforcement learning arXiv HF

#281 ▲42 ★12 ❝0 2026-10-18

CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents

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

Agents Reinforcement learning arXiv Code HF

#284 ▲52 ❝0 2026-10-16

Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning

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

Reinforcement learning Agents arXiv HF

Earlier (archive) 1

▲138 ❝2 2026-09-18

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

CodeMidas turns implemented functionality in codebases into executable coding RL environments using only source code.

Xiaomi MiMo · Bowen Ye, Lei Li, Shicheng Li +16

Code & SWE Reinforcement learning Agents arXiv HF

Search this topic in the archive →