ReThinker: Scientific Reasoning by Rethinking with Guided Reflection and Confidence Control
AI 摘要
ReThinker通过置信度引导的反思和工具使用,显著提升了LLM在复杂科学推理任务上的性能。
主要贡献
- 提出了基于Solver-Critic-Selector架构的置信度感知Agent框架ReThinker
- 设计了反向数据合成流程和自适应轨迹回收策略,用于无监督训练
- 在HLE、GAIA和XBench等benchmark上取得了SOTA结果
方法论
ReThinker通过Solver解决问题,Critic评估置信度,Selector动态调整计算资源和工具调用,并结合反思机制提升性能。
原文摘要
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.