ReThinker: Scientific Reasoning by Rethinking with Guided Reflection and Confidence Control

• URL: http://arxiv.org/abs/2602.04496v1
• Date: Wed, 04 Feb 2026 12:41:52 GMT
• Title: ReThinker: Scientific Reasoning by Rethinking with Guided Reflection and Confidence Control
• Authors: Zhentao Tang, Yuqi Cui, Shixiong Kai, Wenqian Zhao, Ke Ye, Xing Li, Anxin Tian, Zehua Pei, Hui-Ling Zhen, Shoubo Hu, Xiaoguang Li, Yunhe Wang, Mingxuan Yuan,
• Abstract summary: We introduce ReThinker, a confidence-aware agentic framework that orchestrates retrieval, tool use, and multi-agent reasoning.<n> Experiments on HLE, GAIA, and XBench demonstrate that ReThinker consistently outperforms state-of-the-art foundation models.
• Score: 44.113610704492224
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Native Reasoning Models: Training Language Models to Reason on Unverifiable Data [16.065264121785294]
  We introduce NRT (Native Reasoning Training), a novel framework that cultivates complex reasoning.<n>NRT reframes the training problem by treating the reasoning process as a latent variable.<n>NRT achieves state-of-the-art performance among verifier-free methods.
  arXiv  Detail & Related papers  (2026-02-12T04:15:46Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning [103.7657839292775]
  ARM-Thinker is an Agentic multimodal Reward Model that autonomously invokes external tools to ground judgments in verifiable evidence.<n>We train ARM-Thinker with multi-stage reinforcement learning, jointly optimizing tool-calling decisions and judgment accuracy.<n>Our results demonstrate that agentic capabilities significantly enhance both accuracy and interpretability of reward models.
  arXiv  Detail & Related papers  (2025-12-04T18:59:52Z)
• On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN Dataset [16.921428284844684]
  Generalization across Agentic tool-calling environments remains a key unsolved challenge in developing reliable reasoning systems.<n>We present a framework that augments large language models with a lightweight symbolic reasoning layer for structured decomposition and adaptive tool orchestration.
  arXiv  Detail & Related papers  (2025-10-27T00:58:48Z)
• Rewarding the Journey, Not Just the Destination: A Composite Path and Answer Self-Scoring Reward Mechanism for Test-Time Reinforcement Learning [29.778703252962092]
  Reinforcement Learning (RL) has emerged as a powerful paradigm for advancing Large Language Models (LLMs)<n>We develop a novel test-time reward mechanism that operates without external supervision.
  arXiv  Detail & Related papers  (2025-10-20T07:53:51Z)
• ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detection [51.93101033997245]
  Increasing realism of AI-generated images has raised serious concerns about misinformation and privacy violations.<n>We propose ThinkFake, a novel reasoning-based and generalizable framework for AI-generated image detection.<n>We show that ThinkFake outperforms state-of-the-art methods on the GenImage benchmark and demonstrates strong zero-shot generalization on the challenging LOKI benchmark.
  arXiv  Detail & Related papers  (2025-09-24T07:34:09Z)
• ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning [53.817538122688944]
  We introduce Reinforced Meta-thinking Agents (ReMA) to elicit meta-thinking behaviors from Reasoning of Large Language Models (LLMs)<n>ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions.<n> Empirical results from single-turn experiments demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-12T16:05:31Z)
• RaCT: Ranking-aware Chain-of-Thought Optimization for LLMs [30.216174551427443]
  Large language models (LLMs) have demonstrated remarkable potential in text reranking tasks.<n> conventional supervised fine-tuning approaches for specializing LLMs in ranking tasks often lead to significant degradation of the models' general-purpose abilities.<n>This paper presents a novel methodology that strategically combines Chain-of-Thought (CoT) prompting techniques with an innovative two-stage training pipeline.
  arXiv  Detail & Related papers  (2024-12-18T23:24:15Z)
• Soft Expert Reward Learning for Vision-and-Language Navigation [94.86954695912125]
  Vision-and-Language Navigation (VLN) requires an agent to find a specified spot in an unseen environment by following natural language instructions. We introduce a Soft Expert Reward Learning (SERL) model to overcome the reward engineering designing and generalisation problems of the VLN task.
  arXiv  Detail & Related papers  (2020-07-21T14:17:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.