# Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions

arXiv: https://arxiv.org/abs/2607.03935 · HTML: https://mlsanity.com/paper/2607.03935/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 4 Jul 2026.

## Builds on (most cited first, 16 of 16)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model](https://mlsanity.com/paper/2401.02051/) (2024)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [Learning to Discover at Test Time](https://mlsanity.com/paper/2601.16175/) (2026)
- [ThetaEvolve: Test-time Learning on Open Problems](https://mlsanity.com/paper/2511.23473/) (2025)
- [Meta Context Engineering via Agentic Skill Evolution](https://mlsanity.com/paper/2601.21557/) (2026)

## Built on by (most cited first, 12 of 12)

- [Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories](https://mlsanity.com/paper/2608.02276/) (2026)
- [Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses](https://mlsanity.com/paper/2608.08466/) (2026)
- [SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment](https://mlsanity.com/paper/2609.02786/) (2026)
- [Harness-Zero: Harness Distillation via Agent-as-Harness](https://mlsanity.com/paper/2609.24974/) (2026)
- [Auditing Harness Tampering in Self-Improving Agents](https://mlsanity.com/paper/2609.00069/) (2026)
- [Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution](https://mlsanity.com/paper/2608.05651/) (2026)
- [RobustSGPO: Search-Space Control for Agent Harness Evolution](https://mlsanity.com/paper/2609.09646/) (2026)
- [VERSE: Verified Self-Evolving Optimizer for Agent Harnesses](https://mlsanity.com/paper/2610.02616/) (2026)
- [CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution](https://mlsanity.com/paper/2610.10426/) (2026)
- [Recursive Self-Improvement through Multi-Agent Self-Supervision](https://mlsanity.com/paper/2610.12176/) (2026)
- [EverMine: Dissecting the Self-Evolution of Research Capabilities in Long-Horizon Alpha Research](https://mlsanity.com/paper/2609.33524/) (2026)
- [HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery](https://mlsanity.com/paper/2610.17370/) (2026)

## Abstract (arXiv)

Self-evolving frameworks usually optimize task solutions while treating the surrounding harness as fixed. We introduce Harness-Aware Self-Evolving (HASE), an agentic reinforcement-learning framework in which a single model can generate task solutions or edit selected harness components in a multi-turn action space. HASE enables a single Qwen3-8B model to match the text-classification performance of a GPT-OSS-120B model that uses Claude Code as the harness proposer. In alpha factor mining, HASE outperforms the reported GPT-OSS-120B baseline. HASE also repairs imperfect evaluation components and converges to state-of-the-art performance in circle-packing algorithm discovery. These results show that HASE improves the harness and the solution through one unified agentic process.