arXiv AI June 6, 2026 By Chengqi Dong, Chuhuai Yue, Hang He, yandong liu, Fenghe Tang, S Kevin Zhou, Xiaohan Wang, Jiajun Chai, Guojun Yin

TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents

Read the original on arXiv AI →

arXiv:2606. 05784v1 Announce Type: new Abstract: We identify and formally characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents: its uniform broadcast of trajectory-level advantages to all tokens causes valuable tool-use steps in failing trajectories to be penalized no differently from valueless ones.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Aug 3

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization

arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.

By Wonjoong Kim, Yeonjun In, Sangwu Park, Dongha Lee, Chanyoung Park

llms agents reinforcement-learning

arXiv Machine Learning

Jul 7

CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning

arXiv:2601. 15141v2 Announce Type: replace Abstract: Agentic Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to utilize tools like Python interpreters for complex problem-solving.

By Tianshi Xu, Yuteng Chen, Meng Li

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 7

Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry

arXiv:2607. 03702v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong decision-making capabilities in long-horizon interactive tasks, yet they still struggle to effectively leverage failed trajectories: full retries incur high interaction costs, while experience retrieval tends to dilute critical experience signals.

By Weiyang Guo, Zesheng Shi, Longhui Zhang, Zeen Zhu, Min Zhang, Jing Li

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 14

STAMP: Provenance-Guided Credit Assignment for Deep Search Agents

arXiv:2607. 11172v1 Announce Type: new Abstract: Reinforcement learning for deep-search agents has largely focused on trajectory-level scoring -- outcome correctness, citation-aware rewards, and evidence coverage.

By Ke Xu, Han Xu, Xinran Chen, Yuqian Wang, Zhixuan Li, Xiaojian Liu, Changwo Wu, Jianqiang Xia, Yuchen Li

agents reinforcement-learning fine-tuning

arXiv AI

Jun 18

RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents

arXiv:2606. 19047v1 Announce Type: new Abstract: Multi-turn tool-use RL is bottlenecked by the rapid depletion of informative samples in static datasets.

By Ruishan Fang, Siyuan Lu, Chenyi Zhuang, Tao Lin

agents reinforcement-learning

arXiv Machine Learning

Jul 16

TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents

arXiv:2607. 13988v1 Announce Type: new Abstract: Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-training.

By Leitian Tao, Baolin Peng, Wenlin Yao, Tao Ge, Hao Cheng, Mike Hang Wang, Jianfeng Gao, Sharon Li

agents reinforcement-learning fine-tuning benchmarks

Related stories

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization

CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning

Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry

STAMP: Provenance-Guided Credit Assignment for Deep Search Agents

RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents

TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents