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:2608. 02356v2 Announce Type: replace Abstract: Large language model agents increasingly solve complex tasks by composing reusable skills from a library.
By Yue Yao, Shengyuan Wang, Xin Chen, Minke Zhang, Jia He, Bingjun Luo, Tom Gedeon
arXiv:2606. 03056v1 Announce Type: new Abstract: As LLM agents adopt large skill libraries, selecting the right subset becomes a structural problem rather than a similarity-matching one: skills depend on, conflict with, specialize, or duplicate one another, a structure invisible to both full enumeration and embedding similarity.
By Tong Bai, Zhenglin Wan, Pengfei Zhou, Xingrui Yu, Wangbo Zhao, Yang You, Ivor W. Tsang
arXiv:2607. 25853v1 Announce Type: new Abstract: Skills have become an important abstraction for enabling large language model (LLM) agents to reuse past experience in long-horizon interactive tasks.
By Yu Hao, Jinxuan Cai, Qi Zhang, Yawen Li, Zhiqiang Zhang, Chuan Shi, Cheng Yang
GraphSkillEvo introduces a graph-structured representation for agent skills, where each node encodes an execution step and edges capture context-dependent transitions. This structure offers clearer workflow guidance and reduces redundancy compared to unstructured natural-language skills. The authors then present a population-based evolutionary optimization framework that explores this structured skill space, achieving higher accuracy than the baseline SkillOpt across five agent benchmarks.
By Rui Sun, Zhi Zheng, Zhenkun Wang, Zhichao Lu
arXiv:2606. 16774v1 Announce Type: new Abstract: Equipping Large Language Model (LLM) agents with effective skills is crucial for solving complex tasks in real-world systems like OpenClaw.
By Tianyi Lin, Chuanyu Sun, Jingyi Zhang, Changxu Wei, Huanjin Yao, Shunyu Liu, Xikun Zhang, Liu Liu, Jiaxing Huang