The paper introduces SkillCompiler, a framework that transforms self‑evolving agent skills into executable programs to reduce uncertainty from repeated LLM reasoning. It decomposes skills into fine‑grained operations, selectively compiles deterministic parts while retaining LLM reasoning for context‑dependent steps, and reuses validated programs across evolving skills. Experiments on five benchmarks and six model families show SkillCompiler outperforms state‑of‑the‑art methods, improving task performance by up to 32.33%.
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:2609.33772v2 Announce Type: replace
Abstract: Executable environments are critical for post-training agents on tasks that require tool use and multi-step interaction, but constructing executabl...
By Weiyi Xu, Xiaowen Yang, Wen Da, Hang Xu, Canwei Li, Hongjie You, Pusen Dong, Yucheng Zeng, Zhaokai Luo, Mu Chuan
arXiv:2610.10088v1 Announce Type: cross
Abstract: Self-evolving agents distill task-solving experience into skills for future reuse, but these skills can encode incorrect procedures or non-transferab...
By Serin Kim, Kwangwook Seo, Dokyung Song, Jinyoung Yeo, Dongha Lee
The paper introduces EvoSkill-GUI, a training‑free framework that enables GUI agents to evolve their skills during deployment. Each skill is packaged with metadata, executable plans, and recovery rules, and the system follows a reflect‑revise‑reuse loop where the agent instantly revises skills based on execution feedback. Experiments on MobileWorld, AndroidWorld, and OSWorld show consistent performance gains up to +16.2% without any additional training.
By Bofan Chen, Boxuan Zhang, Fei Tang, Zhengxi Lu, Yong Du, Tongbo Chen, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen
arXiv:2606. 26669v1 Announce Type: new Abstract: Agents often repeatedly solve similar task instances from scratch, leading to unnecessary reasoning cost and long execution traces.
By Zhongxin Guo, Danrui Qi, Hanwen Gu, Peng Cheng, Yongqiang Xiong
arXiv:2608. 09253v1 Announce Type: new Abstract: LLM agents are increasingly equipped with skills to perform complex tasks through multi-step reasoning and tool use.
By You Lu, Xinyu Huang, Bihuan Chen, Xin Peng
arXiv:2610.15481v1 Announce Type: new
Abstract: Independently authored skills can impose incompatible requirements, competing preferences, and redundant instructions when jointly loaded by an LLM age...
By Enhao Huang, Xinye Zhao, Yiming Li, Bingrun Yang, Nanjun Zhou, Chunshu Xia, Hongwei Yao, Zhan Qin
HEXIS is a system that compiles agent skills into extended finite state machines, separating skill knowledge from control flow. It uses local instructions within states to guide reasoning and generation, while explicit transition conditions manage execution progress. The incremental compiler maps skill clauses and tool interfaces to state operations, aligns development traces to identify missing operations, and updates are validated through static checks and replay of traces, resulting in improved success rates and reduced execution tokens across benchmarks.
By Minghao LI
arXiv:2606. 01139v1 Announce Type: new Abstract: Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints, and recover from failures.
By Yuxuan Liu, Zhaochen Su, Lingyun Xie, Yuhao Zhang, Qing Zong, Jiahe Guo, Zhongwei Xie, Yiyan Ji, Yauwai Yim, Hongyu Luo, Xiyu Ren, Ruan Chenyu, Haoran Li, Yangqiu Song
arXiv:2605. 28390v2 Announce Type: replace Abstract: Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems.
By Xujun Li, Kehan Zheng, Mingyuan Zhao, Yize Geng, Jinfeng Zhou, Qi Zhu, Fei Mi, Lifeng Shang, Minlie Huang, Hongning Wang
arXiv:2608.29596v1 Announce Type: new
Abstract: Autonomous large language model (LLM) agents increasingly face reliability, context consumption, and execution stability bottlenecks when deployed on c...
By Sanket Badhe, Deep Shah, Priyanka Tiwari, Nehal Kathrotia