DecoEvo: 评分解耦的求解器与评分生成器技能在文本空间中的协同进化

摘要

文本空间优化通过编辑外部自然语言工件而非模型权重来适配大型语言模型（LLM），使得优化后的工件可审查，且模型可被视作黑箱处理。然而，现有文本空间方法大多保持评估标准固定不变。在开放式任务中，这可能成为瓶颈：一旦求解器在评分标准衡量的指标上取得改进，未覆盖的维度就会从优化信号中消失。而简单地对评分标准进行进化也不可靠——当更新由当前求解器的分数决定时，表面上的进步可能源自让评分标准更易满足。我们提出DecoEvo（解耦共同进化），该方法在优化过程中不依赖黄金评分标准，通过解耦目标共同进化求解器技能和评分标准生成技能。求解器技能基于准则级反馈进行更新，而评分标准生成技能则通过独立于求解器总分的互补性审计（涵盖需求覆盖度与响应区分度）进行修正。这种分离使得生成器的更新聚焦于求解器新暴露的弱点，减少对求解器已满足准则的重复强调。在各基准的官方评估下，DecoEvo在五个基准测试和三个LLM主干网络上均优于所有对比方法，在五个基准的平均结果上相较于SkillOpt取得了2.8%至5.0%的相对提升。

English

Text-space optimization adapts large language models (LLMs) by editing external natural-language artifacts rather than model weights, so the optimized artifacts remain inspectable and the model can be treated as a black box. However, most existing text-space methods keep evaluation fixed. On open-ended tasks, this can become a bottleneck: once the solver improves on the criteria a rubric measures, omitted dimensions remain invisible to the optimization signal. Simply evolving the rubric is also unreliable when updates are selected by the current solver's score, because apparent progress can come from making the rubric easier to satisfy. We introduce DecoEvo (Decoupled Co-Evolution), which co-evolves a solver skill and a rubric-generator skill under decoupled objectives without using gold rubrics during optimization. The solver skill is updated using criterion-level feedback, while the rubric-generator skill is revised through complementary audits of requirement coverage and response discrimination that are independent of aggregate solver score. This separation focuses generator updates on newly exposed solver weaknesses, reducing repeated emphasis on criteria the solver already satisfies. Under each benchmark's official evaluation, DecoEvo outperforms all compared methods across five benchmarks and three LLM backbones, yielding 2.8--5.0\% relative gains over SkillOpt in the five-benchmark average.