Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents
2026-06-15 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors study a new way to teach AI agents skills by converting detailed text instructions (SKILL.md files) into small, trainable modules called LoRA adapters. Instead of reading the full instructions every time, the AI loads these adapters to perform the skill, which saves time and computing resources. Their tests show this method improves performance slightly while being more efficient compared to using the full text instructions. They also show that the adapters need to be specifically matched to the skill to work well.
agent skillsSKILL.mdLoRA adaptersruntime contextbehavioral modulesQwen3.6-27BSWE-Skills-Benchskill representationtoken costskill alignment
Authors
Tianyi Zhang, Zhonghao Qi
Abstract
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.