Paper Detail
Yudong Gao, Zongjie Li, Yuanyuanyuan, Zimo Ji, Pingchuan Ma, Shuai Wang
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{gao2026skillreducer,
title = {SkillReducer: Optimizing LLM Agent Skills for Token Efficiency},
author = {Yudong Gao and Zongjie Li and Yuanyuanyuan and Zimo Ji and Pingchuan Ma and Shuai Wang},
year = {2026},
abstract = {LLM-based coding agents rely on \textbackslash{}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\textbackslash{}\% lack routing descriptions entirely, over 60\textbackslash{}\% of body content is non-actionable, and reference files can inject t},
url = {https://arxiv.org/abs/2603.29919},
keywords = {cs.SE},
eprint = {2603.29919},
archiveprefix = {arXiv},
}
{}