Skip to main content
SAICA-KG

Papers

SkillReducer: Optimizing LLM Agent Skills for Token Efficiency

Yudong Gao, Zongjie Li, Yuanyuanyuan, Zimo Ji, Pingchuan Ma, Shuai Wang · 2026 · arXiv

Source →arXiv:2603.29919
failure-mode-taxonomycoding-agentagentic-aibenchmarkempirical

TL;DR

A two-stage optimization framework that achieves a less-is-more effect where removing non-essential content reduces distraction in the context window, and generalize to an independent agent framework is presented.

Abstract

LLM-based coding agents rely on \emph{skills}, pre-packaged instruction sets that extend agent capabilities, yet every token of skill content injected into the context window incurs both monetary cost and attention dilution. To understand the severity of this problem, we conduct a large-scale empirical study of 55,315 publicly available skills and find systemic inefficiencies: 26.4\% lack routing descriptions entirely, over 60\% of body content is non-actionable, and reference files can inject tens of thousands of tokens per invocation. Motivated by these findings, we present \textsc{SkillReducer}, a two-stage optimization framework. Stage~1 optimizes the routing layer by compressing verbose descriptions and generating missing ones via adversarial delta debugging. Stage~2 restructures skill bodies through taxonomy-driven classification and progressive disclosure, separating actionable core rules from supplementary content loaded on demand, validated by faithfulness checks and a self-correcting feedback loop. Evaluated on 600 skills and the SkillsBench benchmark, \textsc{SkillReducer} achieves 48\% description compression and 39\% body compression while improving functional quality by 2.8\%, revealing a \emph{less-is-more} effect where removing non-essential content reduces distraction in the context window. These benefits transfer across five models from four families with a mean retention of 0.965, and generalize to an independent agent framework.

Editorial notes

Large-scale empirical study of 55,315 publicly available agent skills (pre-packaged instruction sets) finding systemic inefficiencies: 26.4% lack routing descriptions, over 60% of body content is non-actionable, and reference files inject tens of thousands of tokens per invocation. Proposes SkillReducer, a two-stage compression framework evaluated on 600 skills and the SkillsBench benchmark, achieving 48% description and 39% body compression while improving functional quality by 2.8%. The 'less-is-more' finding directly evidences context_pollution as a supervision-relevant failure mode. Relates to SAICA-KG failure modes: context_pollution, scope_creep. Useful for arguing that context curation is a first-class supervision activity, not just a cost optimization.

View raw YAML on GitHub →