Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

SkillZip: New Graph Compression Method Boosts LLM Agent Skill Libraries by 3.46x

AI By Crimson AI Hugging Face Papers 13 August 2026 · 00:00 12 views
Share: X Telegram

Hugging Face researchers introduce SkillZip, a contract-preserving graph compression framework that compresses procedural skills into executable macros, achieving up to 12.2-point performance gains and a 3.46x compression ratio.

SkillZip: New Graph Compression Method Boosts LLM Agent Skill Libraries by 3.46x

Key points

As large language models (LLMs) increasingly operate as agents, their procedural knowledge is stored in reusable skill packages that are loaded at inference time. However, as these libraries grow, a key challenge emerges: how to expose the smallest sufficient executable context under limited context budgets. Existing systems often struggle to reuse routines below the whole-skill level, preserve procedural contracts during compression, and keep compressed routines executable and expandable.

To address this, researchers at Hugging Face propose SkillZip, an execution-aware procedural abstraction framework that performs contract-preserving compression over section-level graphs. SkillZip rewrites recurring contract-valid motifs into reversible ported macros while preserving boundary signatures, dependency closure, verifier reachability, and source-level expansion. At inference time, it hydrates a compact, dependency-closed context and expands macros only when required.

The framework also includes ReZip, a component that integrates new skills and revises risky macros using execution evidence. This allows the compressed library to evolve as skills change, addressing the challenge of updating compressed libraries over time.

In experiments on technical and embodied agent benchmarks, SkillZip consistently outperformed the strongest baseline by up to 12.2 points, achieving a 3.46x compression ratio with 99.2% dependency preservation and 98.7% verifier reachability. Scaling analyses further confirmed robust retrieval across skill libraries ranging from 200 to 100,000 skills.

MetricValue
Performance gain vs. strongest baselineUp to 12.2 points
Compression ratio3.46x
Dependency preservation99.2%
Verifier reachability98.7%
Skill library size range200 to 100K skills
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

0
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

0
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

0