SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing
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 workspa
Record details
Published: 12 June 2026
Source: arXiv
Category: Research
Topics: Agents & autonomy · Transparency · Environment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Extracting Semantics: LLM-Guided Automatic Population of Robot Ontology from URDF
arXiv · 10 June 2026
Counterfactual Shapley Credit Assignment
arXiv cs.LG · 18 July 2026
A Decoupled Human-in-the-Loop System for Controlled Autonomy in Agentic Workflows
arXiv · 24 April 2026
Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce
arXiv cs.AI · 3 August 2026
Audio Spatially-Guided Fusion for Audio-Visual Navigation
arXiv · 2 April 2026
Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild
arXiv · 30 March 2026
How to cite this record
ethics.ai (12 June 2026), “SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing,” evidence record 1068, https://ethics.ai/record/1068 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.