Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

• URL: http://arxiv.org/abs/2609.05571v1
• Date: Fri, 04 Sep 2026 03:37:06 GMT
• Title: Grounded Skill Synthesis from Code at Scale for Agentic Intelligence
• Abstract summary: Existing methods face two limitations: trajectory-based synthesis requires interactions with specific environments, while document-derived skills may lack executable evidence and verification.<n>We present Code2Skill, a fully automated pipeline that transforms selected code units into implementation-anchored records of atomic operations, composite repositories, and recurring patterns.<n>Code2Skill produces CodeSkillBank, a grounded bank of 1,006,822 accepted records with workflow, boundary, provenance, and source-evidence metadata.
• Score: 22.319997851901714
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reusable skills give agents transferable procedural knowledge, making scalable acquisition essential for extending agents beyond prior experience. Existing methods face two limitations: trajectory-based synthesis requires interactions with specific environments, while document-derived skills may lack executable evidence and verification. Source code offers a complementary path: it requires no prior agent experience yet provides executable evidence for grounding abstractions. We present Code2Skill, a fully automated pipeline that transforms selected code units into implementation-anchored records of atomic operations, composite workflows, and recurring patterns, then verifies each record through source-body-blind reconstruction and source-aware comparison. Applied to 19,769 popular, actively maintained GitHub repositories, Code2Skill produces CodeSkillBank, a grounded bank of 1,006,822 accepted records with workflow, boundary, provenance, and source-evidence metadata. Across 72 protocol-matched evaluations covering nine model settings and eight benchmarks, models augmented with retrieved CodeSkillBank skills improve by 11.7% on average over matched baselines and outperform them in 57 cases. Under a unified downstream interface, Code2Skill also outperforms trajectory-derived skill banks on all seven shared benchmarks, showing that repository-derived skills can provide useful procedural knowledge before agents accumulate sufficient interaction experience. Skills synthesized from tested AI-generated code achieve a 93.50% pass rate, compared with 93.00% for human-written code, providing initial evidence that the pipeline can expand with the growing volume of AI-generated software. Overall, Code2Skill transforms procedural knowledge embedded in repositories into grounded, verifiable, and transferable agent skills.

Related papers

• Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills [86.15447717549154]
  We present DisCo, a skill-powered research agent that creates skills and uses them during research.<n>We call this missing layer operational knowledge, the know-how that separates knowing a method from making it work.
  arXiv  Detail & Related papers  (2026-09-02T15:49:41Z)
• SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents [16.77727447235193]
  We present SkillCorpus, a framework that aggregates, curates, matches, and evaluates the open skill ecosystem at scale.<n>It filters 821,000 crawled skills through a multi-stage pipeline into 96,401 skills organised by a 16-class taxonomy and three quality facets (utility, robustness, safety)<n>We evaluate end-to-end across three benchmarks (SkillsBench, GDPVal, QwenClawBench), two harnesses, and two open backbones with a frontier robustness check.
  arXiv  Detail & Related papers  (2026-07-17T01:55:17Z)
• SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing [81.51044612408793]
  SkillAudit is a framework for evolving agent skills without ground-truth feedback.<n>To turn behavioral differences into edit guidance, SkillAudit uses Process-Aligned Contrastive Evaluation.<n>It routes edits through two pipelines: Refine removes noisy or irrelevant guidance from broadly useful skills, while Repair replaces passages that conflict with the task.
  arXiv  Detail & Related papers  (2026-06-12T08:20:09Z)
• SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior [23.11308948097101]
  Current benchmarks rarely distinguish what a Skill says from how it is organized.<n>We study this distinction through Progressive Disclosure, where a concise root file points agents to supporting resources on demand.<n>We present SkillJuror, a framework for evaluating Skill writing paradigms.
  arXiv  Detail & Related papers  (2026-06-10T01:11:50Z)
• Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents [27.965275812765015]
  Anything2Skill is a taxonomy-guided framework that compiles heterogeneous external knowledge into reusable, retrievable, and executable skills for agents.<n>We show that Anything2Skill combined with RAG achieves 98.85% and 94.10% success rates, respectively.
  arXiv  Detail & Related papers  (2026-06-08T10:24:32Z)
• Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence [56.25095230687242]
  Coding agents often over-trust their own local validation routines and declare success on artifacts that satisfy surface checks.<n>This problem is especially acute in conversion, where prior evaluation is outcome-driven.<n>Across blind conversion attempts, the best system reaches 26.7--28.9% overall pass rate despite Spec pass rates up to 91.1%.<n>This suggests that failures stem more from contract-misaligned self-validation than from limited budget or backbone strength.
  arXiv  Detail & Related papers  (2026-05-27T19:57:15Z)
• SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents [15.669318649782285]
  We introduce SkillGenBench, a benchmark for evaluating skill generation pipelines under a unified protocol.<n>A generator receives raw corpora and produces standardized skill artifacts, which are then executed under fixed harnesses.<n> Experiments across a range of skill-generation methods and backbones show substantial performance variation.
  arXiv  Detail & Related papers  (2026-05-18T17:28:36Z)
• SWE-chat: Coding Agent Interactions From Real Users in the Wild [70.18158706281724]
  SWE-chat is the first large-scale dataset of real coding agent sessions collected from open-source developers in the wild.<n>The dataset currently contains 6,000 sessions, comprising more than 63,000 user prompts and 355,000 agent tool calls.
  arXiv  Detail & Related papers  (2026-04-22T17:08:19Z)
• SkillRouter: Skill Routing for LLM Agents at Scale [18.540967600258607]
  Given a user task, the system must identify relevant skills before downstream planning or execution.<n>Existing agent stacks often rely on progressive disclosure, exposing only skill names and descriptions while hiding the full implementation body.<n>We present Skill, a compact 1.2B full-text retrieve-and-rerank pipeline.
  arXiv  Detail & Related papers  (2026-03-23T18:23:59Z)
• SoK: Agentic Skills -- Beyond Tool Use in LLM Agents [6.356997609995175]
  Agentic systems increasingly rely on reusable procedural capabilities, textita.k.a., agentic skills, to execute long-horizon reliably.<n>This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update)<n>We analyze the security and governance implications of skill-based agents, covering supply-chain risks, prompt injection via skill payloads, and trust-tiered execution.
  arXiv  Detail & Related papers  (2026-02-24T13:11:38Z)
• Hybrid-Gym: Training Coding Agents to Generalize Across Tasks [59.95803522351185]
  In this paper, we describe some transferable skills that are shared across diverse tasks.<n>We propose a training environment, Hybrid-Gym, consisting of a set of scalable synthetic tasks.<n>Experiments show that agents trained on our synthetic tasks effectively generalize diverse real-world tasks.
  arXiv  Detail & Related papers  (2026-02-18T19:30:55Z)
• Cross-modal Retrieval Models for Stripped Binary Analysis [62.89251403093734]
  BinSeek is the first two-stage cross-modal retrieval framework for stripped binary code analysis.<n>It consists of two models: BinSeekEmbedding is trained on large-scale dataset to learn the semantic relevance of the binary code.<n>BinSeek-Reranker learns to carefully judge the relevance of the candidate code to the description with context augmentation.
  arXiv  Detail & Related papers  (2025-12-11T07:58:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.