# 从原始经验到技能运用：模型生成智能体技能的系统性研究

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-22 08:00
- AIHOT 分数：55
- AIHOT 链接：https://aihot.virxact.com/items/cmpkktloq07w2sl01dudcls7u
- 原文链接：https://arxiv.org/abs/2605.23899

## AI 摘要

语言智能体通过复用从经验中提取的结构化技能来提升能力。本研究系统评估了智能体技能的完整生命周期（经验生成、技能提取与技能运用），构建了涵盖五个多样化任务领域的效用评估框架。研究发现，模型生成的技能平均有益，但存在显著的负面迁移现象；技能的效用与模型规模或任务基线强度无关。研究最终提出了一种元技能，用于指导技能提取过程，以提升技能质量并减少负面迁移。

## 正文

Language agents increasingly improve by reusing skills -- structured procedural artifacts distilled from past experience. In particular, domain-level and model-generated skills are especially promising. They offer fast adaptation within a domain by encoding domain-specific recurring procedures, and they scale beyond labor-intensive hand-crafting. However, while extraction methods continue to proliferate, understanding remains limited, with no comprehensive study spanning the full skill lifecycle -- experience generation, skill extraction, and skill consumption -- to ask whether such skills actually work, when they work, and what makes them succeed or fail. To close this gap, we build a utility-grounded evaluation framework that provides systematic experimental results across extractors and target agents, covering five diverse agentic task domains. We find that model-generated skills are beneficial on average but exhibit non-trivial negative transfer, and that neither extractors nor targets behave uniformly. A model can be a strong extractor yet a weak consumer, or vice versa, with skill utility independent of model scale or baseline task strength. To explain these patterns, we then dissect each lifecycle stage in depth, analyzing how experience composition shapes skill quality, what properties characterize useful skills, and how the same skill transfers across different consumers. Finally, we translate these findings into a concrete meta-skill that guides skill extraction toward the features tied to actual utility, which consistently improves skill quality across domains and substantially reduces negative transfer.