VERSE: Verified Self-Evolving Optimizer for Agent Harnesses
cs.AI, cs.CL, cs.LG
Submitted: 2026-10-02
Updated: 2026-10-02
Comments: 45 pages, 13 figures, 15 tables
Code: https://github.com/wzekai/VERSE
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents
- EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
- From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
- HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
- SIA: Self Improving AI with Harness & Weight Updates
- HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
- Recursive Harness Self-Improvement
- CodeTracer: Towards Traceable Agent States
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- SPEAR: Code-Augmented Agentic Prompt Optimization
- Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions
- HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- TTHE: Test-Time Harness Evolution
- The Last Harness You'll Ever Build
- MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves
- SePO: Self-Evolving Prompt Agent for System Prompt Optimization
- MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-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
- Agents' Last Exam
- 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