# SkillZip Pro: Execution-Aware Dynamic Compression of Progressively Loaded Skills for Self-Evolving Agents

arXiv: https://arxiv.org/abs/2608.30785 · HTML: https://mlsanity.com/paper/2608.30785/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 18 of 18)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Learning to Compress Prompts with Gist Tokens](https://mlsanity.com/paper/2304.08467/) (2023)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models](https://mlsanity.com/paper/2310.05736/) (2023)
- [RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation](https://mlsanity.com/paper/2310.04408/) (2023)
- [Compressing Context to Enhance Inference Efficiency of Large Language Models](https://mlsanity.com/paper/2310.06201/) (2023)
- [SkillOpt: Executive Strategy for Self-Evolving Agent Skills](https://mlsanity.com/paper/2605.23904/) (2026)
- [SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation](https://mlsanity.com/paper/2406.14991/) (2024)
- [SkillReducer: Optimizing LLM Agent Skills for Token Efficiency](https://mlsanity.com/paper/2603.29919/) (2026)
- [SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision](https://mlsanity.com/paper/2606.01139/) (2026)
- [SkillGrad: Optimizing Agent Skills Like Gradient Descent](https://mlsanity.com/paper/2605.27760/) (2026)
- [The Minimum Description Length Principle for Pattern Mining: A Survey](https://mlsanity.com/paper/2007.14009/) (2020)
- [Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents](https://mlsanity.com/paper/2606.16769/) (2026)
- [Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents](https://mlsanity.com/paper/2605.19604/) (2026)
- [SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure](https://mlsanity.com/paper/2608.11079/) (2026)

## Abstract (arXiv)

Production agent skills are directory bundles, not isolated prompts. The root is loaded at activation; references, schemas, scripts, assets, and nested subskills are loaded only when an execution path needs them. Compressing only the root misses most deployment cost and may move branch-specific details into the always-loaded context. Flattening instead destroys progressive-loading boundaries. We introduce method, an evaluation-free compressor for complete, progressively loaded skill bundles. It leaves the agent harness unchanged and emits an ordinary directory. The method combines two safeguards. First, it compresses across files, removing content from a reference or subskill when the root or a declared environment contract already provides it. Second, it preserves routing, so every required file and directly callable entry remains reachable after rewriting. Users can configure method along two independent axes. One-Shot mode rebuilds the full bundle; Continual mode reuses state and applies Zip-on-Write after each evolution patch. Persistent compression rewrites the shipped bundle to reduce storage and runtime context. Transient compression keeps that bundle byte-identical and builds a task-specific view, reducing only per-run context after build cost. Entry contracts mark private, public, and conditional resources; a multi-entry audit preserves standalone public subskills. On a production content-moderation skill evaluated by our industrial multi-round harness, method removes hl38% of skill bundle tokens and hl10.4% of end-to-end per-run tokens with no quality loss, while an unprotected 71% configuration loses up to 26 accuracy points to one-sided false positives. On a multi-entry bundle, method effeciently reduces token cost while near-perfectly preserving every route and public entry.