SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure· 无评估技能压缩助力自进化代理
Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes. Over time, the same requirement is often restated in several branches, examples, and warnings, while common action sequences are copied rather than reused. The resulting skill becomes expensive to inject and difficult to maintain. Generic prompt compression is ill-suited to this setting because a skill is not a flat passage: its name and description define when it applies, its workflow controls execution, its tool and output contracts constrain validity, and rare exceptions may remain essential even when no sampled task activates them. Evaluation-guided compression can test these behaviors, but it introduces rollouts, cost, and dependence on the compression-time evaluation set. We present
提出无评估的技能压缩方法，助力自进化代理更高效地复用技能。
- 核心方法
- 通过发现可复用的结构，提出了一种无需评估的技能压缩方法SkillZip，有效减少了技能的冗余和维护成本。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 自进化代理在累积技能时，由于重复复制常见的操作序列而非复用，导致技能变得难以维护和注入成本高昂。
- 关键实验
- 未提供
- 主要贡献
- SkillZip方法减少了技能的冗余，提高了技能的复用性，降低了技能的维护成本和注入成本。
- 意义与局限
- 该方法有助于提高自进化代理的效率和灵活性，但其有效性和泛化能力需要进一步的实验验证。