Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification

arXiv:2608.27311 · cs.AI · Submitted 2026-08-27 · Read on arXiv

cs.AI

Submitted: 2026-08-27

Updated: 2026-08-27

Comments: 17 pages, 6 figures

Code: https://github.com/jhxu5214/HarnessLens

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

Terminology

• Verification — 87× in this paper · explained in 2 episodes
• Benchmark — 30× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Adaptation — 4× in this paper · explained in 1 episode
• Agent Harness — 4× in this paper · explained in 2 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Analyzer — 2× in this paper · explained in 1 episode
• Generalization — 2× in this paper · explained in 13 episodes
• Agentic System — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Budget-Constrained Optimization — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Online Adaptation — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Text-to-SQL — 1× in this paper · explained in 3 episodes

Sources

• Continual Harness: Online Adaptation for Self-Improving Foundation Agents
• Recursive Harness Self-Improvement
• Meta-Harness: End-to-End Optimization of Model Harnesses
• Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting
• $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
• MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
• Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
• From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• AutoHarness: improving LLM agents by automatically synthesizing a code harness
• Living-Harness Is an Interactive-Agent Evolver
• HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution
• ReCreate: Reasoning and Creating Domain Agents Driven by Experience
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
• MemoHarness: Agent Harnesses That Learn from Experience
• TTHE: Test-Time Harness Evolution
• Code as Agent Harness
• Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
• $\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge

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