harness感知自进化：共同进化模型权重、harness和任务解决方案
Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions
AI总结：
研究提出HASE框架，通过单模型在多轮动作空间生成任务解决方案或编辑harness组件。能使单模型匹配高性能模型文本分类性能，在alpha因子挖掘中超越基线，还能修复评估组件，在算法发现中达最优性能。
摘要：
自进化框架通常将周围的harness视为固定来优化任务解决方案。我们引入了harness感知自进化（HASE），这是一个智能强化学习框架，其中单个模型可以在多轮动作空间中生成任务解决方案或编辑选定的harness组件。HASE使单个Qwen3 - 8B模型能够匹配使用Claude Code作为harness提议者的GPT - OSS - 120B模型的文本分类性能。在alpha因子挖掘中，HASE优于报告的GPT - OSS - 120B基线。HASE还修复了不完美的评估组件，并在圆填充算法发现中收敛到最优性能。这些结果表明，HASE通过一个统一的智能过程改进了harness和解决方案。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
