Evidence-Calibrated Runtime Reconstruction for Agent Skills Across Heterogeneous Coding Agents

arXiv:2608.08793 · cs.CL · Submitted 2026-08-09 · Read on arXiv

Xueping Gao

cs.CL

Submitted: 2026-08-09

Updated: 2026-08-11

Comments: 17 pages, 1 figure, 6 tables. Submitted to PROFES 2026. Code and artifacts: https://github.com/hellogxp/skill-runtime-intelligence

Code: https://github.com/hellogxp/skill-runtime-intelligence

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Trace — 16× in this paper · explained in 2 episodes
• Harness — 14× in this paper · explained in 2 episodes
• Accuracy — 9× in this paper · explained in 1 episode
• Verifier — 9× in this paper · explained in 2 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• Provenance — 6× in this paper · explained in 5 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Verification — 3× in this paper · explained in 2 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Progressive Disclosure — 2× in this paper · explained in 2 episodes
• Abstention — 1× in this paper · explained in 1 episode
• Agent Harness — 1× in this paper · explained in 2 episodes
• Agentic Coding — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Modularity — 1× in this paper · explained in 9 episodes
• Multi-Agent System — 1× in this paper · explained in 7 episodes
• Ontology — 1× in this paper · explained in 2 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes

Sources

• AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
• From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
• SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• Auditing Agent Harness Safety
• Skill Coverage: A Test Adequacy Metric for Agent Skills
• Harness-Bench: Evaluating Agent Harnesses across Models and Realistic Workflows
• AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering