SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Xiaofan Bai, Hongqiang Lin, Chao Liu, Yantao Zhang, Xuan Jin, Xipeng Cao, Yuhong Li
• Venue: arXiv: cs.AI
• Published: 2026-08-11
• Collected: 2026-08-12
• URL: http://arxiv.org/abs/2608.11079v1
• PDF: https://arxiv.org/pdf/2608.11079v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

The paper presents SkillZip, an evaluation-free method for compressing skills by finding their shortest faithful structural explanations. It aims to reduce the repetition and expense of injecting and maintaining skills in self-evolving agents.

What the Document Says

• SkillZip is a method for compression of skills.
• It finds the shortest faithful structural explanation of a skill.
• The method is evaluation-free.
• The goal is to reduce repetition and expense in injecting and maintaining skills in self-evolving agents.
• The method states a repeated rule once at the scope where it applies, factors a repeated action sequence into a shared procedure, and keeps only the differences as explicit exceptions.
• It uses a typed minimum description-length objective over a skill contract and a residual.
• The formulation provides simple sharing thresholds, preserves unique rare rules by construction, and supports efficient local updates.
• SkillZip has a one-shot mode and a continual Zip-on-Write mode.

Key Concepts Mentioned

• SkillZip
• evaluation-free method
• skill compression
• self-evolving agents
• reusable skills
• structural explanation
• typed minimum description-length objective
• one-shot mode
• continual Zip-on-Write mode

Claims Made by the Document

• SkillZip is effective and superior in compression performance, generalizability, and cost overhead.

Evidence Used

• Through comprehensive experimental evaluations

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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 SkillZip, an evaluation-free method that compresses a skill by finding its shortest faithful structural explanation. The intuition is explain once, reference many: state a repeated rule once at the scope where it applies, factor a repeated action sequence into a shared procedure, and keep only the differences as explicit exceptions. We formalize this intuition as a typed minimum description-length objective over a skill contract and a residual, subject to a hard coverage constraint for every extracted trigger, workflow edge, tool requirement, obligation, and output field. The formulation provides simple sharing thresholds, preserves unique rare rules by construction, and supports efficient local updates. SkillZip has a one-shot mode with one structured extraction call and deterministic optimization, and a continual Zip-on-Write mode that integrates each self-evolution patch without replaying tasks or reparsing the full history. Through comprehensive experimental evaluations, we demonstrate the effectiveness and superiority of SkillZip in compression performance, generalizability, and cost overhead.