mlsanityData to 7 Oct 2026

MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization

arXiv 2604.12237 ↗First posted 14 Apr 2026cs.LG cs.AI cs.CLcited by 3

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

Abstract (arXiv)

In drug discovery, molecular optimization aims to iteratively refine a lead compound to improve molecular properties while preserving structural similarity to the original molecule. However, each oracle evaluation is expensive, making sample efficiency a key challenge for existing methods under a limited oracle budget. Trial-and-error approaches require many oracle calls, while methods that leverage external knowledge tend to reuse familiar templates and struggle on challenging objectives. A key missing piece is long-term memory that can ground decisions and provide reusable insights for future optimizations. To address this, we present MolMem (Molecular optimization with Memory), a multi-turn agentic reinforcement learning (RL) framework with a dual-memory system. Specifically, MolMem uses Static Exemplar Memory to retrieve relevant exemplars for cold-start grounding, and Evolving Skill Memory to distill successful trajectories into reusable strategies. Built on this memory-augmented formulation, we train the policy with dense step-wise rewards, turning costly rollouts into long-term knowledge that improves future optimization. Extensive experiments show that MolMem achieves 90% success on single-property tasks (1.5× over the best baseline) and 52% on multi-property tasks using only 500 oracle calls. Our code is available at https://github.com/REAL-Lab-NU/MolMem.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 27 of its 45 references that are in the map. First posted on arXiv 14 Apr 2026.

Builds on

27 of 45 references.

References · 27

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2017Billion-scale similarity search with GPUscited by 2,477
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  4. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  5. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  6. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 357
  7. 2025Memory in the Age of AI Agentscited by 285
  8. 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 264
  9. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  10. 2023What can Large Language Models do in chemistry? A comprehensive benchmark on eight taskscited by 179
  11. 2017Deep Reinforcement Learning for De-Novo Drug Designcited by 161
  12. 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?cited by 153
15 more
  1. 2022Sample Efficiency Matters: A Benchmark for Practical Molecular Optimizationcited by 151
  2. 2024LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Datasetcited by 124
  3. 2019ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendationscited by 77
  4. 2023DrugAssist: A Large Language Model for Molecule Optimizationcited by 57
  5. 2020Optimizing Molecules using Efficient Queries from Property Evaluationscited by 50
  6. 2025Rethinking Entropy Interventions in RLVR: An Entropy Change Perspectivecited by 50
  7. 2025ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoningcited by 41
  8. 2020A Deep Generative Model for Molecule Optimization via One Fragment Modificationcited by 36
  9. 2025A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimizationcited by 12
  10. 2025POLO: Preference-Guided Multi-Turn Reinforcement Learning for Lead Optimizationcited by 10
  11. 2025Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QAcited by 9
  12. 2026A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilationcited by 6
  13. 2026TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimizationcited by 5
  14. 2026Patient-Similarity Cohort Reasoning in Clinical Text-to-SQLcited by 3
  15. 2026GlassMol: Interpretable Molecular Property Prediction with Concept Bottleneck Modelscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026CoAct: Co-Active LLM Preference Learning with Human-AI Synergycited by 3
  2. 2026HopRank: Self-Supervised LLM Preference-Tuning on Graphs for Few-Shot Node Classificationcited by 0
  3. 2026SpecOpt: Contact-Diff Reasoning for Agentic Molecule Optimization Toward Binding Specificitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization
  2. 2026MARCO: Multi-Round Agentic Reinforcement for Conditional Molecular Optimization
  3. 2025MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular Optimization
  4. 2026Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis
  5. 2026MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents
  6. 2026Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design
  7. 2026M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization
  8. 2026C-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment for LLMs