Adaptive Skill Granularity for Coding Agents: Runtime Routing and Macro-to-Micro Recovery· 编码代理的自适应技能粒度
Reusable skills allow large language model agents to package task-specific procedures, tool affordances, and execution guidance into modular units. Prior work has largely studied how agents retrieve, compose, or synthesize skills before execution. In coding agents, however, execution poses an additional runtime control problem: the same task may be solved through primitive tool calls, macro skills, or hybrid execution that starts with a macro and falls back to micro-level recovery. We introduce Adaptive Skill Granularity, a framework that treats skill granularity as an action-abstraction policy conditioned on task structure, execution state, and macro-skill failures. The system combines a feature-based granularity controller and a finite-state recovery executor. We evaluate the framework w
提出自适应技能粒度框架，解决编码代理运行时控制问题。
- 核心方法
- 结合基于特征的粒度控制器和有限状态恢复执行器，根据任务结构、执行状态及宏观技能失败情况动态调整技能的粒度。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- 编码代理在解决同一任务时需要灵活选择使用基本工具调用、宏观技能或从宏观到微观的混合执行策略。
- 关键实验
- 未提供
- 主要贡献
- 引入了Adaptive Skill Granularity框架，提高了编码代理在不同条件下的适应性和执行效率。
- 意义与局限
- 此框架对提高编码代理的灵活性和可靠性有重要影响，但当前研究需要更多实验验证其效果和局限性。