DecoEvo：文本空间中求解器與評分標準生成器技能的分数解耦共同進化

摘要

文本空間優化透過編輯外部自然語言產物（而非模型權重）來調整大型語言模型，使優化後的產物保持可檢視性，且模型可作為黑箱處理。然而，現有文本空間方法大多固定評估標準。在開放式任務中，這可能形成瓶頸：一旦解題器在評分量尺衡量的準則上有所改進，其餘未涵蓋的維度便無法傳遞優化訊號。若僅根據當前解題器的分數來更新評分量尺，同樣不可靠——因為表面進步可能源於降低評分量尺的滿足難度。我們提出「解耦協同進化」（DecoEvo），該方法在無需黃金評分量尺的優化過程中，以解耦目標協同進化解題技能與評分量尺生成技能。解題技能根據準則層級的回饋進行更新，而評分量尺生成技能則透過對需求涵蓋率與回應鑑別度的互補審校（獨立於解題總分）進行修正。這種分離使生成器更新聚焦於新揭露的解題弱點，減少反覆強調解題器已滿足的準則。在各基準的官方評估下，DecoEvo 在五項基準測試與三種大型語言模型主幹中均優於所有對比方法，相較於 SkillOpt 在五項基準平均上獲得 2.8% 至 5.0% 的相對提升。

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.