mlsanityData to 14 Oct 2026

Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design

arXiv 2310.14420 ↗First posted 22 Oct 2023cs.AIcited by 17

On the map: LLM reasoning → Clinical and biomedical applications

Abstract (arXiv)

Discovering novel catalysts requires complex reasoning involving multiple chemical properties and resultant trade-offs, leading to a combinatorial growth in the search space. While large language models (LLM) have demonstrated novel capabilities for chemistry through complex instruction following capabilities and high quality reasoning, a goal-driven combinatorial search using LLMs has not been explored in detail. In this work, we present a Monte Carlo Tree Search-based approach that improves beyond state-of-the-art chain-of-thought prompting variants to augment scientific reasoning. We introduce two new reasoning datasets: 1) a curation of computational chemistry simulations, and 2) diverse questions written by catalysis researchers for reasoning about novel chemical conversion processes. We improve over the best baseline by 25.8% and find that our approach can augment scientist's reasoning and discovery process with novel insights.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 28 of its 50 references that are in the map. First posted on arXiv 22 Oct 2023.

Builds on

28 of 50 references.

References · 28

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  4. 2022Galactica: A Large Language Model for Sciencecited by 744
  5. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  6. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  7. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 366
  8. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 364
  9. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
  10. 2020ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Predictioncited by 337
  11. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  12. 2020The Open Catalyst 2020 (OC20) Dataset and Community Challengescited by 246
16 more
  1. 2018Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Predictioncited by 229
  2. 2022Translation between Molecules and Natural Languagecited by 177
  3. 2022Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editingcited by 166
  4. 2022Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanationscited by 159
  5. 2022A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Languagecited by 131
  6. 2022Language Model Cascadescited by 107
  7. 2020Molecular representation learning with language models and domain-relevant auxiliary taskscited by 94
  8. 2023Unifying Molecular and Textual Representations via Multi-task Language Modellingcited by 93
  9. 2023MolXPT: Wrapping Molecules with Text for Generative Pre-trainingcited by 81
  10. 2023ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Textscited by 78
  11. 2020Mapping the Space of Chemical Reactions Using Attention-Based Neural Networkscited by 70
  12. 2023A Text-guided Protein Design Frameworkcited by 64
  13. 2023Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Languagecited by 44
  14. 2022Group SELFIES: A Robust Fragment-Based Molecular String Representationcited by 33
  15. 2023ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedbackcited by 31
  16. 2021Benchmarking Deep Graph Generative Models for Optimizing New Drug Molecules for COVID-19cited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 5; 2026: 4.

17 papers.

Sort:

By area:

  1. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 344
  2. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 135
  3. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 99
  4. 2024A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discoverycited by 96
  5. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74
  6. 2024MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypothesescited by 72
  7. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  8. 2025Dynamic Parallel Tree Search for Efficient LLM Reasoningcited by 42
  9. 2024ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedbackcited by 33
  10. 2024L+M-24: Building a Dataset for Language + Molecules @ ACL 2024cited by 21
  11. 2024GLaM: Fine-Tuning Large Language Models for Domain Knowledge Graph Alignment via Neighborhood Partitioning and Generative Subgraph Encodingcited by 11
  12. 2025MMSciBench: Benchmarking Language Models on Chinese Multimodal Scientific Problemscited by 10
5 more
  1. 2025Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluatorcited by 9
  2. 2025GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysiscited by 8
  3. 2026ChemGraph-XANES: An Agentic Framework for XANES Simulation and Curationcited by 1
  4. 2026Molecular LLM Agents: From Architectural Design to Scientific Autonomycited by 0
  5. 2026When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Chemical reasoning in LLMs unlocks strategy-aware synthesis planning and reaction mechanism elucidation
  2. 2025Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations
  3. 2025SUPERChem: A Multimodal Reasoning Benchmark in Chemistry
  4. 2026Reasoning-Driven Design of Single Atom Catalysts via a Multi-Agent Large Language Model Framework
  5. 2025Training a Scientific Reasoning Model for Chemistry
  6. 2025A Scientific Reasoning Model for Organic Synthesis Procedure Generation
  7. 2025MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models
  8. 2026From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models