将技能文档转为可动态加载的行为模块，降低大模型推理开销。
Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents
- 用LoRA适配器替代运行时技能文本，实现行为级技能封装
- 在21项技能上提升通过率最高5.2个百分点，每步节省6.6%令牌开销
- 适合需要高效、可复用智能体技能的系统开发者
Agent技能通常以人类可读的SKILL.md文件形式存在，虽便于查看和重用，但需反复注入运行时上下文。本文提出Skill-to-LoRA（S2L），一种以行为为中心的技能表示方法：离线阶段使用完整SKILL.md生成技能引导演示；在线阶段省略原始文档，仅动态加载对应的LoRA适配器来激活所学技能行为。在SWE-Skills-Bench的21项技能子集上评估Qwen3.6-27B模型，相比无技能和完整文本基线，S2L分别提升通过率2.9和5.2个百分点，同时每步令牌成本相较完整文本提示减少6.6%。在18/21项技能上优于完整文本，在15/21项上优于无技能基线。控制实验表明性能提升依赖于技能专属适配器对齐：错误适配器与共享适配器均导致性能下降。结果表明，许多程序化技能可从运行时指令转化为可训练、可动态加载的行为模块。代码将在录用后发布。
原文摘要 · Abstract (English)
Agent skills are commonly distributed as SKILL.md files: human-readable procedural documents that describe workflows, tools, resources, and domain conventions. While convenient for inspection and reuse, this design requires the same reusable procedure to be repeatedly injected into the runtime context. We propose Skill-to-LoRA(S2L), a behavior-centric skill representation that replaces runtime skill text with skill-specific LoRA adapters. Rather than compressing the skill document itself, S2L models the behavioral change induced by the skill text: offline, the complete SKILL.md is used to synthesize skill-guided demonstrations; online, the full document is omitted and the corresponding LoRA adapter is dynamically loaded to activate the learned skill behavior. We evaluate S2L with Qwen3.6-27B on a 21-skill subset of SWE-Skills-Bench. Compared with the no-skill and Full Skill Text baselines, S2L improves pass rate by 2.9 and 5.2 percentage points, respectively, while reducing per-step token cost by 6.6% relative to Full Skill Text prompting. S2L matches or improves Full Skill Text on 18/21 skills and the no-skill baseline on 15/21 skills. Control experiments further show that the gains depend on skill-specific adapter alignment: Wrong-LoRA and Shared-LoRA both reduce performance. These results suggest that many procedural agent skills can be converted from runtime instructions into trainable, dynamically loadable behavioral modules. Code will be released upon acceptance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。