arXiv AI June 17, 2026 By Yanwei Cui, Xing Zhang, Yulong Zhang, Li Shao, Xiaofeng Shi, Guanghui Wang, Peiyang He

Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning

arXiv:2606. 17591v1 Announce Type: new Abstract: Training-free verbal reinforcement learning enables LLM agents to learn from world feedback -- objective signals such as dynamic task outcomes, market returns, or demand forecasts -- by extracting verbal rules from experience and injecting them as context, updating the agent's behavior without parameter changes.

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

arXiv AI

Jun 2

AGENTCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

arXiv:2606. 02461v1 Announce Type: new Abstract: Language agents spend substantial inference time solving individual tasks, yet the experience acquired in one episode is often underutilized in future episodes.

By Yiheng Shu, Bernal Jim\'enez Guti\'errez, Saisri Padmaja Jonnalagedda, Yuguang Yao, Huan Sun, Yu Su

agents benchmarks

arXiv AI

Jun 3

AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

arXiv:2606. 02461v2 Announce Type: replace Abstract: Language agents spend substantial inference time solving individual tasks, yet the experience acquired in one episode is often underutilized in future episodes.

By Yiheng Shu, Bernal Jim\'enez Guti\'errez, Saisri Padmaja Jonnalagedda, Yuguang Yao, Huan Sun, Yu Su

agents benchmarks

arXiv AI

Jul 24

PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning

arXiv:2607. 21419v1 Announce Type: new Abstract: In long-horizon LLM agent reinforcement learning, weak policies often repeat similar failures, producing uninformative rollout trajectories and limiting effective policy optimization.

By Yipeng Shi, Zhipeng Ma, Yue Wang, Qitai Tan, Yang Li, Peng Chen, Zhengzhou Zhu

llms agents reinforcement-learning benchmarks

arXiv Machine Learning

Jul 10

When Does Continual Learning Require Learning

arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?

By Anne Harrington, Nayan Saxena, Michael Murphy, Anastasia Borovykh, Zeyu Yun, Sridhar Kamath, Ara Eindra Kyi, Trevor Darrell, Jitendra Malik, Yutong Bai

llms agents reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Jun 2

Regime-Adaptive Continual Learning for Portfolio Management

arXiv:2606. 00143v1 Announce Type: cross Abstract: Financial markets are inherently non-stationary, exhibiting frequent regime shifts and structural changes that render traditional Portfolio Management (PM) approaches ineffective.

By Chaofan Pan, Lingfei Ren, Linbo Xiong, Yonghao Li, Wei Wei, Xin Yang

agents fine-tuning

arXiv Machine Learning

Aug 3

Learning Stateful Predictive Knowledge From Experience

arXiv:2607. 28638v1 Announce Type: cross Abstract: As large language model (LLM) agents increasingly learn from experience, they primarily rely on trajectory-level reflection to extract insights.

By Yan Song, Xidong Feng, Bo Liu, Xinyu Cui, Haotian Fu, Zichen Liu, Mengyue Yang, Cheng Deng, Jian Zhao, Jun Wang

llms agents nlp reinforcement-learning efficiency

Related stories

AGENTCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning

When Does Continual Learning Require Learning

Regime-Adaptive Continual Learning for Portfolio Management

Learning Stateful Predictive Knowledge From Experience