From the 3 of 28 linked papers with an AI index.
28 papers
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
Zishan Xu, Zhiyuan Yao, Yuxin Chen +9
Training large language model agents for long-horizon tool use typically relies on interactions with real or synthesized executable environments, whose construction and verificatio…
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao +10
Reinforcement learning (RL) with verifiable rewards constructs trajectory-level advantage estimates, yet it often fails to credit the few pivotal decisions that determine outcomes…
Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance
Zhuowen Han, Jinwei Xiao, Zhengxi Lu +9
Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models (LLMs). While Group Relative Policy Optimization (GRPO)…
VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation
Kangning Zhang, Yixing Li, Shuai Shao +9
The paper proposes Visual Attribution Distillation (VAD), a counterfactual method that isolates the visual component of teacher corrections in multimodal on‑policy distillation and…
SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
Zhiyuan Yao, Yuxin Chen, Zhengxi Lu +13
SkillRise introduces a reinforcement‑learning framework that lets large language model agents learn and reuse transferable skills across related tasks by curating a skill document…
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Jinyang Wu, Shuo Yang, Zhengxi Lu +8
The paper introduces SEED, a framework that extracts reusable natural-language skills from on-policy trajectories and distills them back into the policy to provide dense token-leve…