Scientific Reasoning in Language Models

Overview

The field studies whether language models can do more than recall scientific facts: interpret data, connect evidence, design tests, explain mechanisms, and generate useful hypotheses. Common approaches include chain-of-thought and structured reasoning traces, retrieval and tool use, multi-agent collaboration, and training with expert examples, simulators, or reinforcement learning with verifiable rewards. Evaluation spans scientific question answering, mathematics and physics problems, papers and tables, multimodal data, and interactive experimental workflows. Models are improving on specialized tasks, but reliable evidence use, robust execution, and mechanistic understanding remain difficult, and correct answers do not always show that a model reasoned scientifically.

Latest papers

CardsList

167 papers29 papers in the last four weeks, down 24% on the four weeks before. 0.2% of all new papers.

  1. DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning

    Mar 9, 2026Chi-Min Chan, Ehsan Hajiramezanali, Xiner Li +6Process Reward ModelsWeak-to-Strong Generalization

  2. X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes

    Mar 5, 2026Tianxi Gao, Yufan Cai, Yusi Yuan +1Structured Reasoning in Language ModelsReasoning Evaluation

  3. BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning

    Mar 4, 2026Tarjei Paule Hage, Markus J. BuehlerStructural EngineeringRL for Language Model Reasoning

  4. Phi-4-reasoning-vision-15B Technical Report

    Mar 4, 2026Jyoti Aneja, Michael Harrison, Neel Joshi +3VLM ReasoningMLLM Reasoning

  5. OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured Agents

    Mar 3, 2026Yichao Feng, Haoran Luo, Zhenghong Lin +4Multi-Agent LLMsMulti-Agent Orchestration

  6. CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning

    Mar 1, 2026Xinyu Zhu, Yihao Feng, Yanchao Sun +5LLM ReasoningSynthetic Data Generation for Language Models

  7. Full-Stack Domain Enhancement for Combustion LLMs: Construction and Optimization

    Feb 27, 2026Quanjia Xiao, Weimin Ouyang, Zonglin Yang +4Domain Adaptation for LLMsScientific Reasoning in Language Models

  8. SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation

    Feb 26, 2026Jiahao Zhao, Feng Jiang, Shaowei Qin +5LLM EvaluationScientific Reasoning in Language Models

  9. Sci-CoE: Co-evolving Scientific Reasoning LLMs via Geometric Consensus with Sparse Supervision

    Feb 12, 2026Xiaohan He, Shiyang Feng, Songtao Huang +3Scientific Reasoning in Language ModelsLanguage Model Reasoning Evaluation

  10. Universe of Thoughts: A Computational Framework for Creative Reasoning in Large Language Models

    Nov 25, 2025Yuto Suzuki, Farnoush Banaei-KashaniComputational CreativityComputational Cognitive Modeling

  11. Eigen-Agent: Adaptive Multi-Agent Scientific Reasoning with Monitor-Based RAG

    Sep 25, 2025Xiangru Tang, Wanghan Xu, Yujie Wang +13Scientific Reasoning in Language ModelsMulti-Agent Reasoning

  12. Physics: Benchmarking Foundation Models on University-Level Physics Problem Solving

    Mar 26, 2025Kaiyue Feng, Yilun Zhao, Yixin Liu +4LLM EvaluationPhysical Reasoning

  13. A systematic framework for generating novel experimental hypotheses from language models

    Aug 9, 2024Kanishka Misra, Najoung KimChild Language AcquisitionScientific Reasoning in Language Models