Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI

arXiv:2609.38143 · cs.AI, cs.CL, cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.AI, cs.CL, cs.LG

Submitted: 2026-09-29

Updated: 2026-10-01

Code: https://github.com/qiancheng-apodex/MetaSkill-AI4AI

Terminology

• Benchmark — 27× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Verification — 5× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Agent Skills — 3× in this paper · explained in 1 episode
• Agentic System — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Agent Harness — 2× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Procedural Knowledge — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Self-Evolving Agents — 1× in this paper · explained in 2 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• AIDE: AI-Driven Exploration in the Space of Code
• Meta-Harness: End-to-End Optimization of Model Harnesses
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
• Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
• SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
• Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows
• Meta Context Engineering via Agentic Skill Evolution

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection