MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908961923399680 |
|---|---|
| author | Wang, Ziqing Wen, Yibo Pandy, Abhishek Liu, Han Ding, Kaize |
| author_facet | Wang, Ziqing Wen, Yibo Pandy, Abhishek Liu, Han Ding, Kaize |
| contents | 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 (\textbf{Mol}ecular optimization with \textbf{Mem}ory), 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$\times$ 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12237 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization Wang, Ziqing Wen, Yibo Pandy, Abhishek Liu, Han Ding, Kaize Machine Learning Artificial Intelligence Computation and Language 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 (\textbf{Mol}ecular optimization with \textbf{Mem}ory), 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$\times$ 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. |
| title | MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2604.12237 |