arXiv cs.CL· Kexin Ding, Yang Zhou, Can Jin, Feng Tong, Mu Zhou, Dimitris N. Metaxas·· 11 小时前AI 评分34
Agent 技能评估与演化：框架与基准综述
Agent Skill Evaluation and Evolution: Frameworks and Benchmarks
AI 导读
一篇综述系统梳理了 Agent 技能从孤立创建转向评估驱动的自动化演化，将演化归纳为执行反馈、轨迹蒸馏、压缩和强化学习四类范式。文章还分析了六类以技能为中心的基准，指出基准覆盖的结构性缺口、权衡关系与指标丰富度问题，并提出构建可泛化、高效且可验证安全的技能生态的开放方向。
正文 · 原文
Abstract:The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evaluation becomes critical to ensuring their utility, quality, and safety in real-world applications. Consequently, the field is undergoing an emerging paradigm shift from isolated skill creation to automated, evaluation-driven skill evolution. In this survey, we systematically examine the landscape of skill evolution and evaluation beyond foundational skill creation. We categorize evolution into four distinct paradigms, spanning execution feedback, trajectory distillation, compression, and reinforcement learning, showing how each element contributes to improving skill utility and reliability. We also provide an analysis of six skill-centric benchmark categories, identifying structural gaps in benchmark coverage, trade-offs, and metric richness to advance skill research. Finally, we identify open directions for building skill ecosystems that are generalizable, efficient, and verifiably safe. The project URL is this https URL
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2606.11435 [cs.CL] |
| (or arXiv:2606.11435v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.11435 arXiv-issued DOI via DataCite |
Submission history
From: Kexin Ding [view email]
[v1]
Tue, 9 Jun 2026 20:43:23 UTC (531 KB)
[v2]
Mon, 2 Nov 2026 18:56:20 UTC (547 KB)
来源：arXiv cs.CL · arxiv.org