arXiv AI

CODESKILL: Learning Self-Evolving Skills for Coding Agents

CODESKILL is an LLM-based framework that learns to extract, evolve, and maintain procedural skills from coding-agent trajectories. It treats skill extraction and skill-bank management as a learnable policy trained with reinforcement learning, using a hybrid reward combining rubric-based skill quality and verifiable execution feedback. Experiments on EnvBench, SWE-Bench Verified, and Terminal-Bench 2 demonstrate that CODESKILL raises average pass rates by 11.03 over a no-skill baseline and by 5.10 over the strongest prompt-based or memory baseline while keeping a compact skill bank.

arXiv Computation and Language
Oct 27

Hierarchical Skill Evolution for Coding Agent

arXiv:2610.35616v1 Announce Type: new Abstract: Skills provide agents with reusable experience to guide future decisions without modifying the underlying model. However, coding trajectories are often...

By Jun Gao, Yun Peng, Changhai Zhou, Yuhan Zhu, Xiangyu Zeng, Shiyang Zhang Yuhua Zhou, Luozheng Qin, Qian Qiao, Xiaoteng Ma, Baian Chen Weiyi Shang, Zhen Ming Jack Jiang, Lizhi Liao, Xiaoxue Ren
arXiv AI
Jun 2

ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL

arXiv:2606. 01619v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) enables LLM agents to improve continuously from environment rewards, yet the resulting policies do not systematically accumulate reusable strategies that generalize across tasks.

By Zelin He, Haotian Lin, Boran Han, Wei Zhu, Haoyang Fang, Bernie Wang, Xuan Zhu, Runze Li, Matthew Reimherr
arXiv AI
Aug 12

CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification

arXiv:2604. 01687v3 Announce Type: replace Abstract: Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address.

By Hanrong Zhang (Steve), Shicheng Fan (Steve), Henry Peng Zou (Steve), Yankai Chen (Steve), Zhenting Wang (Steve), Jiayu Zhou (Steve), Chengze Li (Steve), Wei-Chieh Huang (Steve), Yifei Yao (Steve), Kening Zheng (Steve), Xue (Steve), Liu, Xiaoxiao Li, Philip S. Yu
arXiv Machine Learning
Oct 8

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

SkillRL is a framework that enhances large language model agents by automatically discovering and evolving skills from raw experience. It builds a hierarchical skill library called SkillBank, uses an adaptive retrieval strategy for heuristics, and allows the skill library to co‑evolve with the agent’s policy during reinforcement learning. These techniques reduce token usage and improve reasoning, achieving state‑of‑the‑art results on ALFWorld, WebShop, and seven search‑augmented tasks, outperforming baselines by 15.3% and remaining robust as task complexity grows.

By Peng Xia, Jianwen Chen, Hanyang Wang, Jiaqi Liu, Kaide Zeng, Yu Wang, Siwei Han, Yiyang Zhou, Xujiang Zhao, Haifeng Chen, Zeyu Zheng, Cihang Xie, Huaxiu Yao
arXiv Computation and Language
Nov 4

Agent Skill Evaluation and Evolution: Frameworks and Benchmarks

The paper surveys the evolving field of agent skill evaluation and evolution, emphasizing the shift from isolated skill creation to automated, evaluation-driven development. It categorizes skill evolution into four paradigms—execution feedback, trajectory distillation, compression, and reinforcement learning—and analyzes six skill-centric benchmark categories to highlight gaps and trade-offs. The authors outline open research directions for building generalizable, efficient, and verifiably safe skill ecosystems.

By Kexin Ding, Yang Zhou, Can Jin, Feng Tong, Mu Zhou, Dimitris N. Metaxas
arXiv Computation and Language
Nov 9

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

MemSkill redefines memory operations in large language model agents as learnable and evolvable skills, enabling agents to extract, consolidate, and prune information from interaction traces more flexibly. It uses a controller to select relevant skills, an LLM-based executor to generate skill-guided memories, and a designer that reviews failures to refine or add new skills, forming a closed‑loop improvement cycle. Experiments on datasets such as LoCoMo, LongMemEval, HotpotQA, and ALFWorld show that MemSkill outperforms strong baselines and generalizes across settings, while analyses reveal how skills evolve over time.

By Haozhen Zhang, Quanyu Long, Jianzhu Bao, Tao Feng, Weizhi Zhang, Haodong Yue, Wenya Wang
arXiv AI
Jun 19

Playful Agentic Robot Learning

arXiv:2606. 19419v1 Announce Type: cross Abstract: Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reusable skills are acquired only after explicit instructions.

By Junyi Zhang, Jiaxin Ge, Hanjun Yoo, Letian Fu, Zihan Yang, Yaowei Liu, Raj Saravanan, Shaofeng Yin, Justin Yu, Dantong Niu, Zirui Wang, Roei Herzig, Ken Goldberg, Yutong Bai, David M. Chan, Ion Stoica, Angjoo Kanazawa, Jiahui Lei, Haiwen Feng, Trevor Darrell