mlsanityData to 14 Oct 2026

Agentic Molecular Recovery via Molecule-Aware Exploration

arXiv 2606.05847 ↗First posted 4 Jun 2026cs.AIcited by 0

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

Text-guided molecular generation with LLMs often yields invalid SMILES. We argue that invalid drafts should be addressed through a shift from validity-oriented repair to identity-preserving molecular recovery: the objective is not only to restore chemical validity, but also to preserve target-relevant structural cues and recover the molecular identity implied by the description. This perspective reveals the limitations of existing correction strategies. Post-hoc repair can recover validity while distorting key structures, LLM-only correction can introduce unintended global drift, and generic agentic correction remains constrained by greedy single-candidate trajectories even when equipped with executable RDKit edit tools. To address these limitations, we propose AMREC, which couples molecule-aware mismatch tracking with expanded candidate exploration and trajectory-level selection. On invalid ChEBI-20 drafts from three backbone models, AMREC achieves the strongest overall recovery profile across structural, exact-match, and string-level metrics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 57 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

28 of 57 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery12 May
  2. 2025MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular Optimization27 May
  3. 2024AgentDrug: Utilizing Large Language Models in An Agentic Workflow for Zero-Shot Molecular Editing17 Oct

Other references · 25

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Large Language Modelscited by 780
  3. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  4. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  5. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 364
  6. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 305
  7. 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 208
  8. 2018Optimization of Molecules via Deep Reinforcement Learningcited by 200
  9. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskscited by 195
  10. 2023What can Large Language Models do in chemistry? A comprehensive benchmark on eight taskscited by 185
  11. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  12. 2022Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editingcited by 166
13 more
  1. 2018Syntax-Directed Variational Autoencoder for Structured Datacited by 103
  2. 2023BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associationscited by 100
  3. 2023Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspectivecited by 92
  4. 2023MolXPT: Wrapping Molecules with Text for Generative Pre-trainingcited by 81
  5. 2023DrugAssist: A Large Language Model for Molecule Optimizationcited by 59
  6. 2025ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoningcited by 41
  7. 2022Group SELFIES: A Robust Fragment-Based Molecular String Representationcited by 33
  8. 2024Text-Guided Molecule Generation with Diffusion Language Modelcited by 31
  9. 2024LICO: Large Language Models for In-Context Molecular Optimizationcited by 26
  10. 2024A quantitative analysis of knowledge-learning preferences in large language models in molecular sciencecited by 18
  11. 2024Large Language Models are In-Context Molecule Learnerscited by 18
  12. 2024Text-guided Diffusion Model for 3D Molecule Generationcited by 5
  13. 2025How to Make Large Language Models Generate 100% Valid Molecules?cited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026MoleCode unlocks structural intelligence in large language models
  2. 2026Constraint-Aware Corrective Memory for Language-Based Drug Discovery Agents
  3. 2025MolEditRL: Structure-Preserving Molecular Editing via Discrete Diffusion and Reinforcement Learning
  4. 2025SynCraft: Guiding Large Language Models to Predict Edit Sequences for Molecular Synthesizability Optimization
  5. 2026Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design
  6. 2025MolErr2Fix: Benchmarking LLM Trustworthiness in Chemistry via Modular Error Detection, Localization, Explanation, and Revision
  7. 2026SureRoute: Toward a Hallucination-Free Self-Improving Platform for Retrosynthesis ↗
  8. 2026Rethinking Molecular Text Representations for LLMs: An Empirical Study