Across four benchmarks spanning heterogeneous tasks, SkillFocus achieves the best held-out accuracy on all four, outperforming the strongest competing result by 5.7 points on average while using 24\% fewer evolution tokens on average than the closest iterative baseline.
Abstract
Agent skill evolution seeks to improve reusable procedural guidance for large language model (LLM) agents through iterative revision. Existing methods base each revision mainly on execution trajectories or feedback, leaving recurring behavioral requirements across tasks implicit and tying revision to the behavior of the current skill. We introduce SkillFocus, which decomposes recurring task requirements into a capability space that remains fixed as the skill evolves, separating what tasks require from how the current skill behaves. SkillFocus maps current task outcomes to this space to identify the capability that leaves the most tasks unresolved, then uses that capability to determine what to revise and which evidence to use. Across four benchmarks spanning heterogeneous tasks, SkillFocus achieves the best held-out accuracy on all four, outperforming the strongest competing result by 5.7 points on average while using 24\% fewer evolution tokens on average than the closest iterative baseline. Controlled studies further show that capabilities derived from recurring task requirements outperform task-semantic and execution-derived alternatives, while randomizing task--capability assignments reduces final accuracy by up to 20.2 points. Matching evidence to the selected capability increases candidate gain by 4.4 points under prioritized revision.
SkillVine is proposed, an automatic skill-evolution framework that formulates skill evolution as a graph search problem and employs a branching exploration strategy, and achieves a balance between exploration and exploitation.
Agent Skills package procedural guidance and resources for reuse, but a relevant Skill does not necessarily improve task performance. Existing studies characterize Skill content and evaluate downstream performance, yet provide limited explanations of how utility depends on content, execution configuration, and multi-Sk...
Yu Cheng, De-Hai Zhao, Zhong-Xin Liu et al.· 0 citations
COBRA-Skills is introduced, an efficient framework that formulates skill optimization as budgeted sequential optimization over a dynamically evolving candidate space and remains robust to changes in the agent harness and performs effectively when the target model itself is used for skill generation and refinement.
Ping-Chen Lu, Xiang-Yi Wang, Xiang Li et al.· 2 citations
Long-running agents accumulate reusable Skills, but a Skill that is semantically relevant to a task is not necessarily worth loading in the current state. We study the applicability question that arises once a candidate Skill is known: should it be loaded in the current state? We propose SkillApt, which uses matched WI...
Shuang-Quan Guo, Xiao-Bo Sui, Fei Jiang et al.· 4 citations
SkillAdam, an Adam-inspired framework for optimizing discrete and non-differentiable skill documents, is introduced, an Adam-inspired framework for optimizing discrete and non-differentiable skill documents with substantially fewer optimization iterations and lower cost than prior methods.
Gao-Yuan Li, Mei-Hao Fan, Yi-Zhe Liu et al.· 5 citations· ⚡3
Memory-augmented reinforcement learning strengthens LLM agents'ability to solve complex long-horizon tasks. Skills are one such form of memory, pairing instructions with an applicability condition over task types. However, retaining every skill indiscriminately as the policy improves lets obsolete or harmful entries ac...
Yuyao Ge, Yi-Wei Wang, Yu-Chen He et al.· 2 citations