# Compression, structure, and executor capability: a controlled real-cost decomposition of language-model agent skill optimisation

arXiv: https://arxiv.org/abs/2607.03048 · HTML: https://mlsanity.com/paper/2607.03048/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## Placed in

- LLM agents and tool use / [Agent skill learning and evolution](https://mlsanity.com/agents/agent-skill-learning-and-evolution/)

## Builds on (most cited first, 9 of 9)

- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [Does Prompt Formatting Have Any Impact on LLM Performance?](https://mlsanity.com/paper/2411.10541/) (2024)
- [SkillReducer: Optimizing LLM Agent Skills for Token Efficiency](https://mlsanity.com/paper/2603.29919/) (2026)
- [From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills](https://mlsanity.com/paper/2604.24026/) (2026)
- [SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement](https://mlsanity.com/paper/2606.10546/) (2026)
- [SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior](https://mlsanity.com/paper/2606.11543/) (2026)
- [Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments](https://mlsanity.com/paper/2602.16653/) (2026)
- [Skill Availability and Presentation Granularity in Large-Language-Model Agents: A Controlled SkillsBench Study](https://mlsanity.com/paper/2605.31408/) (2026)
- [What Should a Skill Remember? Quality--Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model Agents](https://mlsanity.com/paper/2606.09421/) (2026)

## Abstract (arXiv)

Agent skills, reusable instruction artefacts supplied to a tool-using language model, are increasingly optimised by shortening, structural rewriting, stronger-model compilation, and scoped loading, on the assumption that a smaller or better-organised skill lowers cost while preserving success. That assumption is rarely tested with quality and real monetary cost measured on the same runs and the contributing factors separated. This study reports a controlled decomposition over ten skill-delivery conditions, 40 software-engineering tasks, and three repetitions per cell (1,200 rollouts), separating no-skill execution, raw skills, deterministic shortening, linear and structured rendering from a shared semantic ledger, scoped loading, and the compiler and executor model tiers. Quality is the verifier pass rate at task level; cost is solve-stage token cost at standard provider prices, with a token-volume-normalised view for robustness and compilation cost amortised separately. The task is the unit of inference, intervals are task-clustered, and the contrast family is multiplicity-controlled. Deterministic shortening is close to the raw baseline but does not establish non-inferiority within the preset margin. Structured rendering and scoped loading lower pass rate on the compact executor without lowering cost, and structured rendering is indistinguishable from linear text at matched content. The only contrast surviving correction is executor capability, which raises pass rate by 27 percentage points at roughly five times the real cost, with compiler tier showing no robust effect. Under real prices no optimised representation reaches a practical break-even. The evidence indicates that executor capability is the dominant lever and that no representation strategy improves over the raw skill on either executor tier.