LLM-as-an-Improver：将验证转化为更优候选
LLM-as-an-Improver: Turning Verification into Better Candidates
- Fujitsu Limited（富士通株式会社）
- The University of Tokyo（东京大学）
- RIKEN center for AIP（理化学研究所革新智能统合研究中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出LLM-as-an-Improver和Verify--Repair--Reselect方法，利用验证反馈生成并重新选择改进候选，在代码生成和推理基准上优于固定池选择，并能恢复正确解。
AI中文摘要：
基于验证器的选择通过生成多个候选解决方案并使用验证器选择最有希望的一个来提升LLM性能。然而，现有方法通常仅将验证视为排序步骤，并在固定候选池被评估后丢弃其反馈。在本文中，我们探讨验证是否也能改进候选集本身。为此，我们引入LLM-as-an-Improver并提出Verify--Repair--Reselect (VRR)方法，该方法利用验证反馈生成并重新选择改进后的候选。VRR保留初始胜者，同时有条件地生成三个互补的替代方案：胜者和亚军的修复版本，以及基于新方法的解决方案。它仅使用推理时信息过滤无效和重复的候选，然后在原始评估标准下重新选择最终答案。在多种模型以及代码生成和推理基准上，VRR在许多设置中优于固定池的基于验证器的选择，并且即使初始池中所有候选都不正确，也能恢复正确的解决方案。这些结果凸显了LLM作为改进者的更广泛作用：验证反馈不仅能从现有解决方案中选择，还能构建超出初始池的更强候选。
英文摘要：
Verifier-based selection improves LLM performance by generating multiple candidate solutions and using a verifier to select the most promising one. However, existing methods typically treat verification only as a ranking step and discard its feedback once a fixed candidate pool has been evaluated. In this paper, we ask whether verification can also improve the candidate set itself. To this end, we introduce LLM-as-an-Improver and propose Verify--Repair--Reselect (VRR), which uses verification feedback to generate and reselect improved candidates. VRR retains the initial winner while conditionally generating three complementary alternatives: repaired versions of the winner and runner-up, and a solution based on a new approach. It filters invalid and duplicate candidates using only inference-time information and then reselects the final answer under the original evaluation criteria. Across diverse models and code-generation and reasoning benchmarks, VRR improves over fixed-pool verifier-based selection in many settings and can recover correct solutions even when all candidates in the initial pool are incorrect. These results highlight a broader role for LLMs as improvers: verification feedback can not only select among existing solutions but also construct stronger candidates beyond the initial pool.
