LLM Reasoning

LLM: Large Language Model

This field asks how language models can carry out multi-step inference across mathematics, coding, logic, science, and real-world tasks, and how to tell robust reasoning from pattern matching. Common approaches include chain-of-thought prompting, self-consistency and tree search at inference time, tool use and symbolic verification, and post-training with supervised traces, reinforcement learning from verifiable rewards, or process feedback. Researchers are also exploring latent and recurrent computation to reduce reliance on long written traces, alongside benchmarks that test compositionality, robustness, and long-horizon execution. A central tension is that more computation can improve accuracy but raise cost, while plausible explanations and correct final answers do not by themselves establish faithful, reliable reasoning.

Latest papers

931 papers105 papers in the last four weeks, up 27% on the four weeks before. 0.6% of all new papers.

Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization
Mar 13, 2026Zequn Liu, Kehan Wu, Shufang Xie +5Scientific Reasoning in Language Models Molecular Optimization
Zhongguancun Academy · School of Computer Science and Technology, University of Science and Technology of China · Global Health Drug Discovery Institute
RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction
Mar 13, 2026Hanbum Ko, Chanhui Lee, Ye Rin Kim +4AI-Assisted Scientific Research Language Modeling
Department of Artificial Intelligence, Korea University · Materials Intelligence Lab, LG AI Research · Department of Statistics, Korea University
PLDR-LLMs Reason At Self-Organized Criticality
Mar 12, 2026Burc GokdenLLM Reasoning Implicit Reasoning in Language Models
Fromthesky Research Labs LLC Oregon, USA
TopoBench: Benchmarking LLMs on Hard Topological Reasoning
Mar 12, 2026Mayug Maniparambil, Nils Hoehing, Janak Kapuriya +5Constraint-Guided Reasoning in Language Models Spatial Reasoning Benchmarks
Intercom Research · University College Dublin · University of Galway +3
The Stepwise Informativeness Assumption: When Do Entropy Dynamics Track Reasoning Correctness in LLMs?
Mar 11, 2026Mar Gonzàlez I Català, Haitz Sáez de Ocáriz Borde, George D. Montañez +1LLM Reasoning
University of Cambridge · University of Oxford · Harvey Mudd College
Making Bielik LLM Reason (Better): A Field Report
Mar 11, 2026Adam Trybus, Bartosz Bartnicki, Remigiusz KinasLLM Reasoning Language Modeling
Institute of Philosophy, Jagiellonian University, 52 Grodzka St., Kraków 31-044, Poland · Bielik.ai (Speakleash Foundation), 33/4 Niemczańska St., Wrocław 50-561, Poland
Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
Mar 11, 2026Xinyan Jiang, Ninghao Liu, Di Wang +1LLM Reliability LLM Reasoning
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · King Abdullah University of Science and Technology · Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, China +2
HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation
Mar 11, 2026Wenjing Zhang, Jiangze Yan, Jieyun Huang +7CoT Distillation Language Model Distillation
Data Science & AI Research Institute, China Unicom · Unicom Data Intelligence, China Unicom
Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoning
Mar 10, 2026Jiashu He, Meizhu Liu, Olaitan P Olaleye +9Language Model Decoding Efficient Language Model Reasoning
Oracle AI Science · University of Pennsylvania
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
Mar 10, 2026Zorik Gekhman, Roee Aharoni, Eran Ofek +3Factual Knowledge in Language Models LLM Reasoning
Google Research · Technion - Israel Institute of Technology · Tel Aviv University
Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning
Mar 10, 2026Tiehua Mei, Minxuan Lv, Leiyu Pan +5RL for Language Model Reasoning LLM Reasoning
School of Data Science, Fudan University · University of Chinese Academy of Sciences · College of Intelligence and Computing, Tianjin University
EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning
Mar 10, 2026Chengjun Yu, Xuhan Zhu, Chaoqun Du +4Multimodal Large Language Models Long-Horizon Reasoning
University of Science and Technology of China · Foundation Model Team, Li Auto Inc. · Tsinghua University
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
Mar 10, 2026Peihao Wang, Shan Yang, Xijun Wang +8LLM Reasoning Language Model-Based Control
Amazon · The University of Texas at Austin · Georgia Institute of Technology +2
The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
Mar 10, 2026Subramanyam Sahoo, Aman Chadha, Vinija Jain +1Strategic Reasoning Risks in Language Models LLM Safety Alignment
MARS 4.0 Fellowship, Cambridge AI Safety Hub(CAISH), University of Cambridge · AWS Generative AI Innovation Center, Amazon Web Services, USA · Stanford University +2
Learning When to Sample: Confidence-Aware Selective Sampling for Efficient Chain-of-Thought Reasoning
Mar 9, 2026Juming Xiong, Kevin Guo, Congning Ni +7CoT Reasoning Efficient Language Model Reasoning
1Vanderbilt University · 2Vanderbilt University Medical Center · 3Intuit AI Research
TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning
Mar 8, 2026Mingyue Cheng, Shuo Yu, Chuang Jiang +5LLM Reasoning Memory-Augmented Language Model Agents
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China
Prompt Complexity Dilutes Structured Reasoning: A Follow-Up Study on the Car Wash Problem
Mar 7, 2026Heejin JoLLM Prompting LLM Reasoning
Independent Researcher
Entropy-Aware On-Policy Distillation of Language Models
Mar 7, 2026Woogyeol Jin, Taywon Min, Yongjin Yang +5Language Model Distillation On-Policy Distillation
KAIST AI, Seoul, South Korea · University of Toronto, Ontario, Canada · Vector Institute, Ontario, Canada +1
Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping
Mar 6, 2026Zhenyu Lei, Qiong Wu, Jianxiong Dong +4Language Model Editing LLM Reasoning
University of Virginia · AT&T Chief Data Office · Florida State University
Not Too Short, Not Too Long: How LLM Response Length Shapes People's Critical Thinking in Error Detection
Mar 6, 2026Natalie Friedman, Adelaide Nyanyo, Kevin Weatherwax +4Human-AI Decision Making LLM Reasoning
BTP Innovation, SAP, Palo Alto, CA, USA
LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoning
Mar 6, 2026Denys Pushkin, Emmanuel AbbeLong-Horizon LLM Reasoning Long-Horizon Reasoning
EPFL, Apple
Evaluation of Deontic Conditional Reasoning in Large Language Models: The Case of Wason's Selection Task
Mar 6, 2026Hirohiko Abe, Kentaro Ozeki, Risako Ando +3LLM Reasoning
Keio University, Tokyo, Japan · University of Tokyo, Tokyo, Japan
CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
Mar 5, 2026Hejian Sang, Yuanda Xu, Zhengze Zhou +3CoT Distillation Efficient Language Model Reasoning
X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes
Mar 5, 2026Tianxi Gao, Yufan Cai, Yusi Yuan +1Structured Reasoning in Language Models Reasoning Evaluation
National University of Singapore, Singapore
Enhancing Zero-shot Commonsense Reasoning by Integrating Visual Knowledge via Machine Imagination
Mar 5, 2026Hyuntae Park, Yeachan Kim, SangKeun LeeLLM Reasoning Zero-Shot Learning
Department of Artificial Intelligence, Korea University, 145 Anam-ro, Seungbuk-gu, Seoul, 02841, Republic of Korea · Department of Computer Science and Engineering, Korea University, 145 Anam-ro, Seungbuk-gu, Seoul, 02841, Republic of Korea
$\nabla$ -Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space
Mar 5, 2026Peihao Wang, Ruisi Cai, Zhen Wang +4LLM Reasoning Test-Time Optimization
The University of Texas at Austin · UC San Diego · TTIC +1
T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning
Mar 4, 2026Qinsi Wang, Hancheng Ye, Jinhee Kim +12Structured Reasoning LLM Reasoning
Duke University · UT Austin · Meta
Verify to Amplify: Improving Reasoning via Learned Chain-of-Thought Verification
Mar 3, 2026Maria-Florina Balcan, Avrim Blum, Kiriaki Fragkia +2LLM Evaluation LLM Answer Verification
Carnegie Mellon University · Toyota Technological Institute at Chicago · Northwestern University
Step-Level Sparse Autoencoder for Reasoning Process Interpretation
Mar 3, 2026Xuan Yang, Jiayu Liu, Yuhang Lai +3LLM Interpretability Sparse Autoencoders
Department of Data Science, City University of Hong Kong · Hong Kong Institute of AI for Science, City University of Hong Kong · Li Auto Inc +1
Multi-Agent Debate with Memory Masking
Mar 3, 2026Hongduan Tian, Xiao Feng, Ziyuan Zhao +3Multi-Agent Debate LLM Reasoning
TMLR Group, Hong Kong Baptist University · Search Algorithm Group, WeChat, Tencent

Mar 13, 2026J/K move · Enter open · S save

Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization

Zequn Liu, Kehan Wu, Shufang Xie, Zekun Guo+4

Zhongguancun Academy · School of Computer Science and Technology, University of Science and Technology of China · Global Health Drug Discovery Institute

Scientific Reasoning in Language Models Molecular Optimization Large Language Model-Guided Optimization LLM Reasoning Drug Discovery

Open paper AskPDF arXiv

Emerging reasoning models hold promise for automating scientific discovery. However, their training is hindered by a critical supervision gap: experimental outcomes are abundant, whereas intermediate reasoning steps are rarely documented at scale. To bridge this gap, we propose DESRO, a framework for deciphering scientific reasoning from outcomes. By analyzing shared patterns and key differences within grouped data, a large language model (LLM) can recover the underlying logic. We instantiate this framework in molecule optimization, a pivotal stage in drug discovery that traditionally relies on the iterative reasoning of medicinal chemists. Across 2.3 million molecular property records, our framework infers optimization rationales by grouping molecules with shared fragments, then using an LLM to analyze how structural variations correlate with property differences. Based on the derived data, we train a model that conducts molecule optimization through an interpretable reasoning process. DESRO achieves the highest success rates on 15 out of 18 tasks, spanning both single- and multi-property optimization of bioactivity and ADMET properties. The reasoning process enables robust generalization to out-of-distribution scenarios, including novel property combinations, unseen biological targets, and unseen properties defined solely by natural language descriptions. In retrospective case studies under strict temporal splits, the model autonomously reconstructs expert-level lead optimization trajectories. Additionally, our framework extends beyond molecule optimization to reaction ligand selection. Our results establish deciphering reasoning steps from outcome data as a viable paradigm for enabling scientific reasoning, providing a scalable approach to accelerate scientific discovery.