SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing

• URL: http://arxiv.org/abs/2606.14239v1
• Date: Fri, 12 Jun 2026 08:20:09 GMT
• Title: SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing
• Abstract summary: 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.
• Score: 81.51044612408793
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent skills are structured procedural packages that guide frozen LLM agents in specialized workflows. Skills rarely remain sufficient after deployment: edge cases, API changes, and deployment constraints become visible only through use, making skill evolution a practical necessity. Existing methods depend on privileged feedback such as held-out validation scores, hidden test outcomes, or environment rewards -- signals often unavailable when a practitioner has only a task description and workspace data. We introduce SkillAudit, a framework for evolving agent skills without ground-truth feedback. The key idea is paired trajectory auditing: at each iteration, the same task is executed with and without the candidate skill, isolating how the skill changes agent behavior without external labels. To turn behavioral differences into edit guidance, SkillAudit uses Process-Aligned Contrastive Evaluation (PACE), a cluster of evaluators that maps trajectory divergences to diagnostic signals linked to specific passages in the skill document. A structural verifier, compiled once from the task specification and then fixed, checks task constraints and rolls back harmful updates. SkillAudit routes edits through two pipelines: Refine removes noisy or irrelevant guidance from broadly useful skills, while Repair replaces passages that conflict with the task. Across 89 containerized tasks spanning 8 professional domains, SkillAudit achieves 73.9% average task reward, outperforming an agent without skills (40.9%) and the static expert skill (56.7%). These gains are obtained without accessing hidden tests, reference solutions, or external scoring functions during evolution.

Related papers

• Demystifying Agent Skills: Why They Work-Until They Don't [58.92875630998418]
  Existing evaluations largely measure whether skills improve aggregated task success, leaving a more fundamental question underexplored: emphtextbfWhen do skills help, why do they work, and where do they fail?<n>We isolate the effects of representation, outcome annotation, retrieval difficulty, and cross-framework of skills.<n>We consolidate these observations into a taxonomy of three high-level categories and twelve skill-use modes.
  arXiv  Detail & Related papers  (2026-08-14T07:26:38Z)
• Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills [53.15216425100295]
  We introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a skill controller.<n>The proposer generates challenging tasks conditioned on dynamically sampled skills; the solver explores candidate solutions to push its capability boundaries; and the skill controller collects execution feedback to update and expand the skill library.<n>This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration.
  arXiv  Detail & Related papers  (2026-07-24T17:59:22Z)
• AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows [1.6785141970297952]
  AEVAL (Agentic Evaluation) is a CI-integrated framework that replaces this practice with a deterministic, reproducible test pipeline for agentic skills.<n>Every skill change triggers a test event: the skill runs against a developer declared evaluation contract inside an automated executor.<n>A key ingredient is a structural separation between executor and grader, preventing a subtle but pervasive failure mode.
  arXiv  Detail & Related papers  (2026-07-16T21:33:05Z)
• SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use [21.05387636058484]
  SkillCoach is a self-evolving framework for evaluating and enhancing agentic skill-use.<n>It derives skill-grounded process rubrics from real rollouts and evaluates trajectories along four dimensions.<n>It keeps the external verifier as a separate outcome signal, allowing process quality to be distinguished from accidental task success.
  arXiv  Detail & Related papers  (2026-07-02T08:28:51Z)
• SkillCAT: Contrastive Assessment and Topology-Aware Skill Self-Evolution for LLM Agents [42.30624901249764]
  Current pipelines learn from one trajectory per task, merge candidate skill patches before checking them, and load the full skill corpus before inference.<n>We propose SkillCAT, a training-free framework that separates this process into three stages.<n>We evaluate SkillCAT on common agent benchmarks, including SpreadsheetBench, WikiTableQuestions, and DocVQA.
  arXiv  Detail & Related papers  (2026-06-11T13:12:10Z)
• 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)
• Skill Coverage: A Test Adequacy Metric for Agent Skills [17.60316723069748]
  Agent skills encode reusable procedural knowledge that guides large language model agents across tasks and execution contexts.<n>We introduce skill coverage, a test adequacy metric that treats the skill artifact as the object under test.<n>Applying skill coverage to SkillsBench reveals that existing benchmark executions cover only 39.90 to 43.98% of skill behavior constraints.
  arXiv  Detail & Related papers  (2026-06-09T10:16:05Z)
• What Should a Skill Remember? Quality--Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model Agents [58.87681796862133]
  We study skill rewriting through an economic lens.<n>Our framework profiles skill structure and rewrites skills using information-preservation strategies.<n> Experiments on SkillsBench reveal distinct quality--cost trade-offs across strategies.
  arXiv  Detail & Related papers  (2026-06-08T12:36:51Z)
• COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation [58.84646485020439]
  We present an automated trace-to-skill distillation system for generating person-grounded AI skills.<n> COLLEAGUE.SKILL produces a versioned skill package with two tracks: a capability track for practices, mental models, and decisions, and a bounded behavior track for communication style, interaction rules, and correction history.
  arXiv  Detail & Related papers  (2026-05-29T12:59:08Z)
• SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills [31.23929961213889]
  Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks.<n>We introduce SkillEvolBench, a diagnostic benchmark for evaluating this step from experience reuse to skill formation.<n>We find that current agents often adapt locally but rarely form robust reusable skills.
  arXiv  Detail & Related papers  (2026-05-22T18:23:31Z)
• 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)
• Counterfactual Trace Auditing of LLM Agent Skills [38.396785087675774]
  We introduce a framework for measuring how a skill changes agent behavior.<n>We instantiate CTA on SWE-Skills-Bench with Claude across 49 software engineering tasks.<n>Pass rate changes by only +0.3 percentage points on average, suggesting little aggregate effect.
  arXiv  Detail & Related papers  (2026-05-12T10:56:18Z)
• SkillOS: Learning Skill Curation for Self-Evolving Agents [67.94374107466957]
  We propose SkillOS, an experience-driven RL training recipe for learning skill curation in self-evolving agents.<n>SkillOS pairs a frozen agent executor that retrieves and applies skills with a trainable skill curator that updates an external SkillRepo from accumulated experience.<n>We show that SkillOS consistently outperforms memory-free and strong memory-based baselines in both effectiveness and efficiency.
  arXiv  Detail & Related papers  (2026-05-07T17:31:50Z)
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks [61.89812116484928]
  Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time.<n>We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers.<n>We show curated Skills raise average pass rate by 16.2 percentage points(pp), but effects vary widely by domain.<n>Self-generated Skills provide no benefit on average, showing that models cannot reliably author the procedural knowledge they benefit from consuming.
  arXiv  Detail & Related papers  (2026-02-13T07:06:06Z)

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.