{"ID":5938004,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T15:51:33.870313962Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03935","arxiv_id":"2607.03935","title":"Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions","abstract":"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.","short_abstract":"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. HAS...","url_abs":"https://arxiv.org/abs/2607.03935","url_pdf":"https://arxiv.org/pdf/2607.03935v1","authors":"[\"Haochen Luo\",\"Yi Huang\",\"Sichun Luo\",\"Fengyuan Liu\",\"Lei Li\",\"Zefa Hu\",\"Junlan Feng\",\"Qi Liu\"]","published":"2026-07-04T16:04:30Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[]","has_code":false}