mlsanityData to 14 Oct 2026

MolLean: A Process-Verifiable Language for Chemical Reasoning

arXiv 2610.20459 ↗First posted 14 Oct 2026cs.CL cs.CE cs.PLcited by 0

New in LLM reasoning; no direction yet. LLM reasoning

Abstract (arXiv)

Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a process-verifiable language that grounds chemical reasoning in an explicit molecular state. A layered Lean-based kernel checks state transitions and assertions over molecular readouts, from primitive graph edits to compound transformations. Meanwhile, a typed witness protocol separates native structural checks from externally supplied measurements. We further introduce MolLean-MCP, a stateful tool interface that exposes these transitions, checks, and readouts during generation: the model receives feedback to decide its next action, and rejected actions leave the state unchanged. MolLean supports one-pass trace execution, whole-trace refinement, and interactive reasoning through MolLean-MCP. We evaluate these three modes with direct chain-of-thought on 8,800 matched examples across 12 tasks spanning molecular generation, editing, optimization, and reactions. With Qwen3.6-27B, whole-trace refinement outperforms direct chain-of-thought on all 12 tasks. MolLean-MCP complements whole-trace refinement with stepwise verification feedback, reaching better performance in reaction tasks. Together, these results highlight an executable foundation for chemical reasoning, in which explicit chemical commitments can be checked and revised rather than remaining solely in free-form explanations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 35 references that are in the map. First posted on arXiv 14 Oct 2026.

Builds on

21 of 35 references.

References · 21

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Let's Verify Step by Stepcited by 3,789
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  5. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  6. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  7. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  8. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  9. 2022PAL: Program-aided Language Modelscited by 652
  10. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  11. 2023LeanDojo: Theorem Proving with Retrieval-Augmented Language Modelscited by 427
  12. 2022Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofscited by 291
9 more
  1. 2022Translation between Molecules and Natural Languagecited by 177
  2. 2025Training a Scientific Reasoning Model for Chemistrycited by 56
  3. 2024ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedbackcited by 33
  4. 2024Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generationcited by 25
  5. 2025Chem-R: Learning to Reason as a Chemistcited by 17
  6. 2025MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMscited by 12
  7. 2025Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discoverycited by 12
  8. 2024Structural Reasoning Improves Molecular Understanding of LLMcited by 11
  9. 2026Chemical Chain-of-Thought Functions as a Hallucination-Prone Molecular Scratchpadcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models
  2. 2026MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs
  3. 2025Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations
  4. 2025Bridging the Plausibility-Validity Gap by Fine-Tuning a Reasoning-Enhanced LLM for Chemical Synthesis and Discovery
  5. 2025oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning
  6. 2026SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules
  7. 2026Logos: An evolvable reasoning engine for rational molecular design
  8. 2026MolQuest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation