cs.CLNov 9, 2026

SMO: Compiling Natural Language Skills into Graphs of Reusable State-Move-Outcome Bricks

Authors: Chao Chen, Jiashuo Zhang, Yunhang Shen, Liangyu Lian, Rongrong Ji

Organizations: Xiamen University

Abstract

Large language model agents increasingly rely on reusable natural-language skills, yet growing skill collections remain accumulations of isolated text artifacts that are difficult to compare, deduplicate, and compose. We argue that the reusable content of a skill lies not in its surface wording but in its procedural transitions: which operation to execute under a given state and which observable outcome to produce. Based on this observation, we propose State-Move-Outcome (SMO), a compilation-like framework that decomposes raw skills into reusable procedural bricks and organizes admitted bricks as an externalized symbolic structure. When compiling a skill, SMO first retrieves and composes existing bricks, dynamically connects them through Outcome-to-State conditions, and creates a candidate brick only for an uncovered procedure; the candidate becomes reusable only after validation and admission. Experiments on SkillsBench v1.1 demonstrate that SMO represents 232 rawSkills from 87 underlying tasks with 95 shared bricks, reducing the corresponding skill representations from 366,472 to 149,154 tokens--a 59.3×\mathbf{59.3}\times reduction and 2.46×\mathbf{2.46}\times compression. Across 232 skill-conditioned evaluation instances, SMO raises the average task score from 0.6379\mathbf{0.6379} to 0.7478\mathbf{0.7478} and increases 5/5 Pass instances from 138\mathbf{138} to 164\mathbf{164}, while matching or outperforming rawSkill on 208\mathbf{208} of 232\mathbf{232} instances. It also reduces average runtime token consumption by 38.38%\mathbf{38.38\%}. These results show that compiling natural-language skills into shared procedural units can jointly improve skill reuse, representation efficiency, and downstream execution.

Figures & tables

Explore similar work

May 12, 2026

SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces

Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are typically injected into the agent reasoning loop as contextual guidance once matched to a runtime task, enabling specialized task-solving capabilities. We find that this execution paradigm introduces two major sources of redundancy: irrelevant context injection and repeated skill-specific reasoning and planning. To this end, we propose SkillSmith, a boundary-first compiler-runtime framework that compiles skill packages offline into minimal executable interfaces. By extracting fine-grained operational boundaries from skills, SkillSmith enables agents to dynamically access and execute only the relevant components at runtime, thereby minimizing unnecessary context injection and redundant reasoning overhead. In the evaluation on SkillsBench benchmark, SkillSmith reduces solve-stage token usage by 57.44%, thinking iterations by 42.99%, solve time by 50.57% (2.02x faster), and token-proportional monetary cost by 57.44% compared with using raw-skills. Moreover, compiled artifacts produced by a stronger model can be reused by a smaller or more efficient runtime model, improving task accuracy in cases where raw skill interpretation fails. The source code and data are available at https://github.com/AetherHeart-AI/Aeloon.
Nov 5, 2026

How Much Skill Orchestration Can LLM Agents Compile Away? Execution-Grounded Specialization for Token-Efficient Skill Use

Reusable skills guide large language model (LLM) agents through recurring requests, but each invocation still requires the model to interpret the skill and reconstruct its orchestration. Can agents automatically compile this orchestration into an executable fast path without human intervention? We first study zero-shot skill specialization, which compiles without execution evidence, and find that despite the skill's procedural guidance, incorrect assumptions about runtime bindings can make generated plans brittle and recovery costly. This motivates SkillCache, a one-trace skill specialization method that compiles a completed invocation into a parameterized capsule of programs and natural-language steps, replays it before reuse, and drives it with a plan executor that returns control to the model only when needed, keeping the source skill for recovery. With the Claude Code harness, warm execution of the same request reduces tokens on 87 SkillsBench tasks by 81% with Claude Sonnet 4.6 and by 74% with Claude Opus 4.8 at comparable reward, and capsules stay effective under controlled request changes. Capsules also transfer across models, raising three open-weight models' mean reward by 12-25 percentage points while reducing their tokens by 72-81%, suggesting that execution-grounded compilation is a promising approach to efficient repeated skill use and cross-model transfer.
Sep 30, 2026

SkillSpec: Consensus-Gated Agent Skill Evolution via Representation Specialization

Natural-language skills are textual procedural memories through which large language model (LLM) agents retain reusable task knowledge without updating model weights. Existing methods typically treat skills as either static artifacts or monolithic documents optimized using aggregate validation scores as feedback. However, representing a skill as a monolithic document restricts optimization to its textual content, without explicitly modeling the structure through which procedural knowledge is retrieved and executed. We identify a key distinction between learning what knowledge to retain and determining how to organize it: textual updates should first be validated through execution evidence, after which the retained knowledge should be structured according to its procedural dependencies and retrieval requirements. To this end, we introduce SkillSpec, a two-phase framework comprising consensus-gated evolution and representation specialization. In the consensus-gated phase, complementary editing intents generate complete candidate skills. An update is committed only when paired evaluations reach consensus, requiring sufficient overall improvement and non-negative aggregate paired gain in every repeated evaluation. In the specialization phase, signals of process and redundancy sensitivity derived from the full optimization trajectory, including accepted and rejected candidates, guide the selection of a flat, graph, or hybrid representation.Across six benchmarks and three target language models, SkillSpec improves average success rate over SkillOpt by 6.89%, averaged across the three models. These results demonstrate that reliable skill evolution and representation specialization address complementary objectives: deciding what knowledge to retain and how to structure it for inference.