AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao, Jinyang Wu, Jie Wu, Zhengzhou Cai, Yueqing Sun, Ziang Ye, Linji Hao, Qi Gu, Xunliang Cai, Yongliang Shen, Yujiu Yang

Paper HF Code BIB 🤗 HuggingFace Daily Paper #1

• A critic-free, recursive self-distillation method that provides turn-level credit assignment for long-horizon, multi-turn agentic reinforcement learning.

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

Zhiyuan Yao, Yuxin Chen, Zhengxi Lu, Zishan Xu, Yueqing Sun, Yifu Guo, Yuquan Lu, Zhengzhou Cai, Kangning Zhang, Zhuowen Han, Zi-Han Wang, Ziang Ye, Qi Gu, Xunliang Cai, Weiwen Liu, Yongliang Shen

Paper HF BIB

• A unified RL framework that learns reusable skills across related tasks by organizing instances into progressively challenging sequences.

SDAR: Self-Distilled Agentic Reinforcement Learning

Zhengxi Lu, Zhiyuan Yao, Zhuowen Han, Zi-Han Wang, Jinyang Wu, Qi Gu, Xunliang Cai, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen

Paper HF Code BIB 🤗 HuggingFace Daily Paper #2

• Extends on-policy self-distillation to multi-turn agents, delivering dense token-level guidance on top of coarse trajectory-level rewards.

Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

Huichi Zhou*, Yihang Chen*, Siyuan Guo, Xue Yan, Kin Hei Lee, Zihan Wang, Ka Yiu Lee, Guchun Zhang, Kun Shao, Linyi Yang†, Jun Wang†

Paper HF Code BIB

• Memory-based online reinforcement learning that lets LLM agents continually adapt from experience without updating the underlying model weights.

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges

Zi-Han Wang, Lam Nguyen, Zhengyang Zhao, Mengyue Yang, Chengwei Qin, Yujiu Yang, Linyi Yang

Paper Homepage Code BIB

• A benchmark for machine creativity in code generation — covering combinatorial and exploratory creativity with executable evaluation and the inference-time enhancement strategy EvoRePE.

Alignment for Efficient Tool Calling of Large Language Models

Hongshen Xu*, Zihan Wang*, Zichen Zhu, Lei Pan, Xingyu Chen, Lu Chen, Kai Yu

Paper BIB

• A multi-objective alignment framework that combines probabilistic knowledge-boundary estimation with dynamic decision making to reduce unnecessary tool calls while preserving performance.

Reducing Tool Hallucination via Reliability Alignment

Hongshen Xu, Zichen Zhu, Lei Pan, Zihan Wang, Su Zhu, Da Ma, Ruisheng Cao, Lu Chen, Kai Yu

Paper BIB

• Defines and categorizes tool hallucinations (tool selection vs. tool usage) and introduces reliability-oriented alignment for more robust and efficient tool interaction.