mlsanityData to 14 Oct 2026

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

arXiv 2607.03935 ↗First posted 4 Jul 2026cs.AIcited by 12

Not on the map. Why?

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.

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

16 of 22 references.

References · 16

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  5. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  6. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  7. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  8. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  9. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 398
  10. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 356
  11. 2026Meta-Harness: End-to-End Optimization of Model Harnessescited by 309
  12. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 268
4 more
  1. 2025ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolutioncited by 174
  2. 2026Learning to Discover at Test Timecited by 115
  3. 2025ThetaEvolve: Test-time Learning on Open Problemscited by 64
  4. 2026Meta Context Engineering via Agentic Skill Evolutioncited by 49

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 12.

12 papers.

  1. 2026Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectoriescited by 16
  2. 2026Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnessescited by 7
  3. 2026SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignmentcited by 6
  4. 2026Harness-Zero: Harness Distillation via Agent-as-Harnesscited by 5
  5. 2026Auditing Harness Tampering in Self-Improving Agentscited by 4
  6. 2026Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolutioncited by 2
  7. 2026RobustSGPO: Search-Space Control for Agent Harness Evolutioncited by 1
  8. 2026VERSE: Verified Self-Evolving Optimizer for Agent Harnessescited by 1
  9. 2026CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolutioncited by 1
  10. 2026Recursive Self-Improvement through Multi-Agent Self-Supervisioncited by 1
  11. 2026EverMine: Dissecting the Self-Evolution of Research Capabilities in Long-Horizon Alpha Researchcited by 0
  12. 2026HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discoverycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
  2. 2026Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
  3. 2026HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
  4. 2026Rethinking the Evaluation of Harness Evolution for Agents
  5. 2026HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses
  6. 2026EvolveNet: Collaborative Harness Evolution for Agent Self-Improvement
  7. 2026Harness Evolution as Learning: Approximation, Generalization, and Optimization Limits of Self-Improving Personal Agents
  8. 2026Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses