Large Language Model-Guided Scientific Discovery

Follow this topic Ask about this topic

Momentum

18 papers in the last four weeks, up 80% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 185

All topics

From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data
May 21, 2026Mohammad R. Rezaei, Rahul G. KrishnanResidual Learning In-Context Learning
Department of Computer Science University of Toronto Vector Institute Toronto, ON, Canada
SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules
May 21, 2026Yuxuan Chen, Changwei Lv, Yunduo Xiao +5AI-Assisted Scientific Research Molecular Generation
School of Electronic and Computer Engineering, Peking University, Shenzhen, China · Tsinghua University, Beijing, China · School of Intelligence Science and Technology, Nanjing University, Suzhou, China
LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation
May 21, 2026Zhuo Chen, Xinzhe Yuan, Jianshu Zhang +8AI for Science Bayesian Optimization
equal contribution · Shanghai Artificial Intelligence Laboratory, Shanghai, China · School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China +7
Beyond Text and Tables: Vision-Language Model Integration in ComProScanner for Extracting Materials Data from Scientific Figures with High Accuracy
May 19, 2026Aritra Roy, Enrico Grisan, Chiara Gattinoni +1VLM Evaluation Document Information Extraction
Energy, Materials and Environment Research Centre, London South Bank University, London SE1 0AA, UK. · School of Engineering and Design, London South Bank University, London SE1 0AA, UK. · Bioscience and Bioengineering Research Centre, London South Bank University, London SE1 0AA, UK. +1
Evidence-Grounded Frontier Mapping and Agentic Hypothesis Generation in Nanomedicine
May 18, 2026Christiaan G. A. Viviers, Koen de Bruin, Mirre M. Trines +6Scientific Hypothesis Generation Evidence-Grounded Generation
ARIA Lab, Signal Processing Systems, Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands. · Laboratory of Chemical Biology, Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands. · The Louis Family Laboratory for Targeted Drug Delivery and Personalized Medicine Technologies, Department of Chemical Engineering, Technion - Israel Institute of Technology, Haifa, Israel. +2
Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery
May 18, 2026Xinzhe Yuan, Zhuo Chen, Jianshu Zhang +4Bayesian Optimization Large Language Model-Guided Optimization
Shanghai Artificial Intelligence Laboratory, Shanghai, China · Shanghai Jiao Tong University, Shanghai, China · Harbin Institute of Technology, Harbin, China
LEAP: A closed-loop framework for perovskite precursor additive discovery
May 18, 2026Xin-De Wang, Zhi-Rui Chen, Ze-Feng Gao +3Materials Science Large Language Model-Guided Scientific Discovery
School of Physics, Renmin University of China, Beijing, China · School of Chemistry and Life Resource, Renmin University of China, Beijing, China
Episodic-Semantic Memory Architecture for Long-Horizon Scientific Agents
May 17, 2026Nikola MilosevicLLM Agent Memory Long-Horizon LLM Agents
Serbian Institute for Artificial Intelligence Research and Development, Fruskogorska 1, Novi Sad, Serbia · Bayer A.G., Müllerstrasse 178, 13353 Berlin, Germany
MoleCode unlocks structural intelligence in large language models
May 15, 2026Zhiyuan Yan, Chen Liu, Boxuan Zhao +8Molecular Generation Large Language Model-Guided Scientific Discovery
Peking University Shenzhen Graduage School
Optimized Three-Dimensional Photovoltaic Structures with LLM guided Tree Search
May 15, 2026Michael P. Brenner, Lizzie Dorfman, John C. PlattLarge Language Model-Guided Optimization Large Language Model-Guided Scientific Discovery
Google Research · School of Engineering and Applied Sciences, Harvard University
SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution
May 14, 2026Jiachen Jiang, Huminhao Zhu, Zhihui ZhuLLM-Based Program Synthesis Large Language Model-Guided Scientific Discovery
Department of Computer Science and Engineering The Ohio State University
Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation
May 14, 2026Songyang Gao, Yinghui Xia, Siyi Liu +1Scientific Hypothesis Generation Research Idea Generation
The Hong Kong University of Science and Technology (Guangzhou) · Tsinghua University · The Hong Kong University of Science and Technology
SciPaths: Forecasting Pathways to Scientific Discovery
May 14, 2026Eric Chamoun, Yizhou Chi, Yulong Chen +4Scientific Reasoning Scientific Discovery
University of Cambridge, Cambridge, United Kingdom · Singapore University of Technology and Design, Singapore · The Alan Turing Institute, London, United Kingdom
CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation
May 14, 2026Yuyang Wu, Stefano Falletta, Delia McGrath +1Crystal Structure Generation RL for Generative Models
Tsinghua University Beijing, China · Radical AI · New York University New York, NY, USA
Effective Harness Engineering for Algorithm Discovery with Coding Agents
May 13, 2026Yoichi Ishibashi, Taro Yano, Masafumi OyamadaReward Hacking Automated Algorithm Discovery
NEC Corporation.
PROMETHEUS: Automating Deep Causal Research Integrating Text, Data and Models
May 13, 2026Sridhar MahadevanCausal World Models Causal Attribution
Adobe Research · University of Massachusetts, Amherst
Towards Discovery of Polymers for Insulin Delivery via Physics-Grounded Agentic Workflows
May 12, 2026Martins OtunMolecular Optimization Large Language Model-Guided Optimization
1Algonix AI Ltd., Scotland, United Kingdom
Read, Grep, and Synthesize: Diagnosing Cross-Domain Seed Exposure for LLM Research Ideation
May 12, 2026Yunju Choi, Min SongResearch Idea Generation Large Language Model-Guided Scientific Discovery
1Yonsei University, Seoul, Republic of Korea · 2OnomaAI, Seoul, Republic of Korea.
CVEvolve: Autonomous Algorithm Discovery for Unstructured Scientific Data Processing
May 12, 2026Ming Du, Xiangyu Yin, Yanqi Luo +4Automated Algorithm Discovery Scientific Code Generation
Advanced Photon Source Argonne National Laboratory Lemont, IL, USA
Epistemic Uncertainty for Test-Time Discovery
May 11, 2026Kainat Riaz, Muhammad Ahmed Mohsin, Ahsan Bilal +5RL for Language Models RL Exploration
Stanford University · University of Oklahoma · National University of Sciences and Technology
Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves
May 11, 2026Tousif Islam, Digvijay Wadekar, Tejaswi Venumadhav +4Surrogate Modeling Gravitational-Wave Astronomy
Kavli Institute for Theoretical Physics, University of California Santa Barbara, Kohn Hall, Lagoon Rd, Santa Barbara, CA 93106, USA. · Center for Gravitational Physics, University of Texas at Austin, Austin, TX 78712, USA. · Department of Physics, University of California at Santa Barbara, Santa Barbara, CA 93106, USA. +5
Unlocking LLM Creativity in Science through Analogical Reasoning
May 11, 2026Andrew Shen, Shaul Druckmann, James ZouAnalogical Reasoning Large Language Model-Guided Scientific Discovery
Stanford University
LLM Jaggedness Unlocks Scientific Creativity
May 11, 2026Shray Mathur, J. Anibal Boscoboinik, Esther H. R. Tsai +1Creativity Assessment LLM Evaluation
Center for Functional Nanomaterials, Brookhaven National Laboratory Upton, NY 11973, USA
Hypothesis-Driven Deep Research with Large Language Models: A Structured Methodology for Automated Knowledge Discovery
May 11, 2026Michael ChinDeep Research Agents AI-Assisted Scientific Research
Independent Researcher
LLM-Guided Monte Carlo Tree Search over Knowledge Graphs: Composing Mechanistic Explanations for Drug-Disease Pairs
May 10, 2026Rishabh Jakhar, Michel Dumontier, Remzi CelebiLLM Reasoning with Graphs Scientific Discovery
Institute of Data Science, Department of Advanced Computing Sciences, Maastricht University, The Netherlands
Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery
May 9, 2026Harshit Bisht, Vinay Kumar, Kevin Maik Jablonka +2AI Agents for Scientific Discovery Scientific Hypothesis Generation
Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi · Laboratory of Organic and Macromolecular Chemistry (IOMC), Friedrich Schiller University Jena · Center for Energy and Environmental Chemistry Jena, Friedrich Schiller University Jena +3
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
May 9, 2026Bohan Lyu, Yucheng Yang, Siqiao Huang +25AI Agents for Scientific Discovery Automated Algorithm Discovery
UC Berkeley · Tsinghua University · Purdue University +6
POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles
May 8, 2026Nicolas Menet, Andreas Krause, Abbas RahimiThompson Sampling Black-Box Optimization
IBM Research – Zurich · Department of Computer Science, ETH Zürich
CellScientist: From Execution Feedback to Auditable Model-Revision Trajectories for Cellular Perturbation Prediction
May 8, 2026Mengran Li, Bo Li, Jiaying Wang +7Single-Cell Perturbation Modeling Scientific Workflow Automation
Center for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science and Innovation (HKISI)
Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation
May 8, 2026Sum Kyun Song, Bong Gyun Shin, Jae Yong LeeAI Agents for Scientific Discovery Autonomous Scientific Discovery
Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea · Department of AI Big Data, Daejin University, Pocheon-si, Republic of Korea.

May 21, 2026, cs.LGJ/K move · Enter open · S save

From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data

Mohammad R. Rezaei, Rahul G. Krishnan

Department of Computer Science University of Toronto Vector Institute Toronto, ON, Canada

Residual Learning In-Context Learning Large Language Model-Guided Scientific Discovery Multi-Agent LLMs

Open paper AskPDF arXiv

A persistent challenge in machine learning for scientific applications is jointly achieving prediction and understanding. Statistical models excel on structured data but operate as black boxes, while existing interpretability methods are largely inspective: they answer "which features matter?" but do not articulate how features interact or refine explanations iteratively alongside human understanding. Asking an LLM to predict the target directly forces it to search the entire output space; we instead anchor predictions with a base model and ask the LLM the narrower question of what that model is missing. We introduce Multi-Agent Residual In-Context Learning (MARICL), an agentic framework in which LLM agents analyze where a base-model fails, hypothesize missing structure from high-residual examples provided in context, and produce explicit correction terms refined through multi-turn textual gradient optimization. Across nine benchmarks spanning scientific, biomedical, socioeconomic, and synthetic settings, MARICL improves consistently over its base model on all datasets. To test whether these corrections reflect real structure or batch-specific noise, we freeze formulas learned on one experimental batch of the Cell-Free Protein dataset and apply them (with no retraining and no further LLM calls) to held-out batches. Within the same reagent protocol, the frozen formulas improve predictions in over 92% of cases; across a different protocol, they fail systematically. The success boundary aligns with the biochemistry, not the batch count; direct evidence of mechanistic generalization.

Momentum

Related topics

Latest papers 185