ReThinker：通过引导反思与置信度控制实现科学推理
ReThinker: Scientific Reasoning by Rethinking with Guided Reflection and Confidence Control
AI总结：
ReThinker通过引导反思与置信度控制，提升大语言模型在专家级科学推理任务中的性能
摘要：
专家级的科学推理对于大语言模型仍然具有挑战性，特别是在诸如人类最后考试（HLE）等基准测试中，刚性的工具流水线、脆弱的多智能体协调和低效的测试时间扩展常常限制性能。我们介绍了ReThinker，一种具有置信度意识的代理框架，通过分阶段的求解器-批评者-选择器架构来协调检索、工具使用和多智能体推理。与遵循固定流程不同，ReThinker根据模型置信度动态分配计算，使能够适应性地调用工具、引导多维反思和稳健地进行置信度加权选择。为了支持无需人工标注的可扩展训练，我们进一步提出了一种反向数据合成管道和一种自适应轨迹回收策略，将成功的推理轨迹转换为高质量的监督。在HLE、GAIA和XBench上的实验表明，ReThinker在专家级推理任务上始终优于具有工具的最先进基础模型和现有的深度研究系统，取得了最先进的结果。
英文摘要：
Expert-level scientific reasoning remains challenging for large language models, particularly on benchmarks such as Humanity's Last Exam (HLE), where rigid tool pipelines, brittle multi-agent coordination, and inefficient test-time scaling often limit performance. We introduce ReThinker, a confidence-aware agentic framework that orchestrates retrieval, tool use, and multi-agent reasoning through a stage-wise Solver-Critic-Selector architecture. Rather than following a fixed pipeline, ReThinker dynamically allocates computation based on model confidence, enabling adaptive tool invocation, guided multi-dimensional reflection, and robust confidence-weighted selection. To support scalable training without human annotation, we further propose a reverse data synthesis pipeline and an adaptive trajectory recycling strategy that transform successful reasoning traces into high-quality supervision. Experiments on HLE, GAIA, and XBench demonstrate that ReThinker consistently outperforms state-of-the-art foundation models with tools and existing deep research systems, achieving state-of-the-art results on expert-level reasoning tasks.
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。
