# FineVerify：用于智能体搜索的细粒度自验证框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-30 08:00
- AIHOT 分数：65
- AIHOT 链接：https://aihot.virxact.com/items/cmpwe0tqq022qslsnq45j55og
- 原文链接：https://arxiv.org/abs/2606.00660

## AI 摘要

FineVerify是一种提升智能体搜索任务表现的自验证框架。它通过将问题分解为可验证的子问题，对采样出的候选答案进行逐一验证，并选择聚合得分最高的答案。在四个智能体搜索基准测试中，该框架效果显著：仅用四个采样轨迹，就能将GPT-5-mini的准确率提升8.2个百分点，将Gemini-3-flash平均提升5.6%。使用12个样本时，它能使GPT-5-mini在BrowseComp-Plus上超越前沿模型GPT-5。此外，该框架还能生成可解释的验证轨迹，有助于审查基准测试错误。相关代码与数据已开源。

## 正文

Agentic search requires language model agents to explore many sources and answer complex information-seeking questions. Scaling test-time compute is a promising way to improve these agents, but current approaches can fail, because correct answers are often sparse and score-based selection depends on model calibration. We propose FineVerify, a fine-grained self-verification framework that decomposes each question into checkable sub-questions, verifies sampled candidates against each sub-question, and selects the candidate with the highest aggregated score. This per-check structure turns selection into simpler local judgments and produces scores under the same explicit criteria. Across four agentic search benchmarks and two models, FineVerify consistently outperforms standard scaling baselines. With only four sampled trajectories, it improves GPT-5-mini by 8.2 accuracy points and Gemini-3-flash by 5.6% on average. With 12 samples, FineVerify enables GPT-5-mini to surpass frontier GPT-5 on BrowseComp-Plus. Beyond accuracy, FineVerify produces interpretable verification traces that help audit benchmark errors, suggesting broader applications for inspecting agentic search systems. Code and data are available at https://github.com/XuZhao0/fineverify