mlsanityData to 7 Oct 2026

ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback

arXiv 2402.10980 ↗First posted 15 Feb 2024physics.chem-ph cs.AI cs.CEcited by 32

On the map: LLM reasoning → Clinical and biomedical applications

Abstract (arXiv)

The discovery of new catalysts is essential for the design of new and more efficient chemical processes in order to transition to a sustainable future. We introduce an AI-guided computational screening framework unifying linguistic reasoning with quantum-chemistry based feedback from 3D atomistic representations. Our approach formulates catalyst discovery as an uncertain environment where an agent actively searches for highly effective catalysts via the iterative combination of large language model (LLM)-derived hypotheses and atomistic graph neural network (GNN)-derived feedback. Identified catalysts in intermediate search steps undergo structural evaluation based on spatial orientation, reaction pathways, and stability. Scoring functions based on adsorption energies and reaction energy barriers steer the exploration in the LLM's knowledge space toward energetically favorable, high-efficiency catalysts. We introduce planning methods that automatically guide the exploration without human input, providing competitive performance against expert-enumerated chemical descriptor-based implementations. By integrating language-guided reasoning with computational chemistry feedback, our work pioneers AI-accelerated, trustworthy catalyst discovery.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 35 of its 89 references that are in the map. First posted on arXiv 15 Feb 2024.

Builds on

35 of 89 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design22 Oct

Other references · 34

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  7. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  8. 2022Galactica: A Large Language Model for Sciencecited by 736
  9. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  10. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 342
  11. 2020The Open Catalyst 2020 (OC20) Dataset and Community Challengescited by 246
  12. 2018Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Predictioncited by 225
22 more
  1. 2023What can Large Language Models do in chemistry? A comprehensive benchmark on eight taskscited by 179
  2. 2022Translation between Molecules and Natural Languagecited by 173
  3. 2022Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editingcited by 165
  4. 2023Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Modelscited by 131
  5. 2022A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Languagecited by 129
  6. 2023Emergent autonomous scientific research capabilities of large language modelscited by 127
  7. 2023Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systemscited by 118
  8. 2023Unifying Molecular and Textual Representations via Multi-task Language Modellingcited by 92
  9. 2020Molecular representation learning with language models and domain-relevant auxiliary taskscited by 91
  10. 2023InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discoverycited by 86
  11. 2023MolXPT: Wrapping Molecules with Text for Generative Pre-trainingcited by 81
  12. 2023ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Textscited by 78
  13. 2020Mapping the Space of Chemical Reactions Using Attention-Based Neural Networkscited by 70
  14. 2023GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learningcited by 70
  15. 2023A Text-guided Protein Design Frameworkcited by 61
  16. 2023DrugAssist: A Large Language Model for Molecule Optimizationcited by 57
  17. 2024Developing ChemDFM as a large language foundation model for chemistrycited by 51
  18. 2020An Introduction to Electrocatalyst Design using Machine Learning for Renewable Energy Storagecited by 45
  19. 2023Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Languagecited by 44
  20. 2022Group SELFIES: A Robust Fragment-Based Molecular String Representationcited by 32
  21. 2023ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedbackcited by 30
  22. 2020AiiDA 1.0, a scalable computational infrastructure for automated reproducible workflows and data provenancecited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 12; 2026: 13.

32 papers.

Sort:

By area:

  1. 2024A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discoverycited by 96
  2. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 96
  3. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agentscited by 96
  4. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  5. 2024MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypothesescited by 68
  6. 2025LLM Agents for Education: Advances and Applicationscited by 59
  7. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  8. 2025Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agentscited by 30
  9. 2024LICO: Large Language Models for In-Context Molecular Optimizationcited by 26
  10. 2024L+M-24: Building a Dataset for Language + Molecules @ ACL 2024cited by 21
  11. 2024Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Surveycited by 16
  12. 2025A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimizationcited by 12
20 more
  1. 2024From Generalist to Specialist: A Survey of Large Language Models for Chemistrycited by 11
  2. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physicscited by 11
  3. 2025LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discoverycited by 11
  4. 2025mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Moleculescited by 8
  5. 2025Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Findcited by 7
  6. 2026El Agente Quntur: A research collaborator agent for quantum chemistrycited by 7
  7. 2025AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Upcited by 6
  8. 2025GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysiscited by 6
  9. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 6
  10. 2025Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessmentcited by 5
  11. 2026Context Learning for Multi-Agent Discussioncited by 2
  12. 2026COGTRL: Training LLMs for Scientific Discovery Assistance using Cognitive Traces via Reinforcement Learningcited by 1
  13. 2026DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanationscited by 0
  14. 2026Reaction-network reasoning with frontier models for experimentally confirmed catalyst-selectivity hypothesescited by 0
  15. 2026Networked Intelligence: Active Shared Context Graphs for Human-AI Team Sciencecited by 0
  16. 2026Failures Reveal What Metrics Miss: An Evidence-Driven Agent for Recursive Refinement of ECG Classifierscited by 0
  17. 2026A Modular Agentic Framework for Synthetically Constrained Multi-Objective Hit-to-Lead Optimizationcited by 0
  18. 2026Science Done on a Machine by a Machine: AI Agents in Computational Chemistrycited by 0
  19. 2026TRACE: Transition-Aware Residual Control for Multi-Objective Materials Discoverycited by 0
  20. 2026MAIL: Memory-driven, Adaptive, Incremental, and Literature-grounded Framework for Hypothesis Generation in Chemistrycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Reasoning-Driven Design of Single Atom Catalysts via a Multi-Agent Large Language Model Framework
  2. 2025ChemGraph: An Agentic Framework for Computational Chemistry Workflows
  3. 2025Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Functional Materials Discovery
  4. 2025Chemical reasoning in LLMs unlocks strategy-aware synthesis planning and reaction mechanism elucidation
  5. 2026Autonomous computational catalysis through an agentic research system
  6. 2025Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations
  7. 2025A Scientific Reasoning Model for Organic Synthesis Procedure Generation
  8. 2025ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge