Evaluating the Progression of Large Language Model Capabilities for Small-Molecule Drug Design

• URL: http://arxiv.org/abs/2604.16279v1
• Date: Fri, 17 Apr 2026 17:40:26 GMT
• Title: Evaluating the Progression of Large Language Model Capabilities for Small-Molecule Drug Design
• Abstract summary: We introduce a suite of chemically-grounded tasks spanning molecular property prediction, molecular representation transformations, and molecular design.<n>We formulate these tasks as reinforcement learning environments, enabling a unified approach for evaluation and post-training.<n>A smaller model post-trained on our environments becomes competitive with state-of-the-art frontier models, despite a significantly weaker base model.
• Score: 5.312232639944646
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have the potential to accelerate small molecule drug design due to their ability to reason about information from diverse sources and formats. However, their practical utility remains unclear due to the lack of benchmarks that reflect real-world scenarios. In this work, we introduce a suite of chemically-grounded tasks spanning molecular property prediction, molecular representation transformations, and molecular design. Importantly, we formulate these tasks as reinforcement learning (RL) environments, enabling a unified approach for evaluation and post-training. Across three model families, we find that frontier models are increasingly proficient at chemical tasks, but that there is significant room for improvement, especially in experimental settings with low data. Critically, we show that RL-based post-training can substantially improve performance. A smaller model post-trained on our environments becomes competitive with state-of-the-art frontier models, despite a significantly weaker base model. This suggests a practical route toward employing LLMs in drug discovery; by combining carefully-designed evaluation tasks with targeted post-training, we can both elucidate and close critical capability gaps.

Related papers

• Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling [11.750407280528272]
  Large language models (LLMs) provide a useful generative prior for this problem.<n>Many chemically relevant scoring functions require hours or even days per evaluation, making them prohibitively expensive to use directly during online training.<n>We investigate whether LLMs can learn molecular design strategies from cheaper synthetic tasks that generalize to expensive molecular lead optimization settings.
  arXiv  Detail & Related papers  (2026-09-04T05:05:44Z)
• Learning POMDP World Models from Observations with Language-Model Priors [52.11151769796862]
  Partially-observable Markov decision processes (POMDPs) provide a flexible modeling class for internal world models.<n>We ask whether language-model priors can reduce costly interaction by leveraging prior knowledge.<n>We show that emphPinductor matches the performance and sample efficiency of LLM-based POMDP learning methods.
  arXiv  Detail & Related papers  (2026-05-13T16:18:15Z)
• MolRGen: A Training and Evaluation Setting for De Novo Molecular Generation with Reasonning Models [48.34354151490484]
  We introduce MolRGen, a benchmark and dataset for training and evaluating reasoning-based large language models.<n>First, we propose a setting to evaluate and train models for textitde novo molecular generation and property prediction.<n>Second, we introduce a novel diversity-aware top-$k$ score that captures both the quality and diversity of generated molecules.
  arXiv  Detail & Related papers  (2026-03-18T20:21:04Z)
• MMAI Gym for Science: Training Liquid Foundation Models for Drug Discovery [41.21168385964764]
  MMAI Gym is a one-stop shop molecular data formats and modalities as well as task-specific reasoning, training, and benchmarking recipes.<n>We use MMAI Gym to train an efficient Liquid Foundation Model (LFM) for these applications, demonstrating that smaller, purpose-trained foundation models can outperform substantially larger general-purpose or specialist models on molecular benchmarks.
  arXiv  Detail & Related papers  (2026-03-03T20:51:51Z)
• Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis [51.83339196548892]
  ChemCraft is a novel framework that decouples chemical reasoning from knowledge storage.<n>ChemCraft achieves superior performance with minimal inference costs.<n>This work establishes a cost-effective and privacy-preserving paradigm for AI-aided chemistry.
  arXiv  Detail & Related papers  (2026-01-25T04:23:34Z)
• Foundation Models for Discovery and Exploration in Chemical Space [57.97784111110166]
  MIST is a family of molecular foundation models trained on large unlabeled datasets.<n>We demonstrate the ability of these models to solve real-world problems across chemical space.
  arXiv  Detail & Related papers  (2025-10-20T17:56:01Z)
• Reasoning-Enhanced Large Language Models for Molecular Property Prediction [19.593493317167646]
  Molecular property prediction is crucial for drug discovery and materials science.<n>Existing approaches suffer from limited interpretability, poor cross-task generalization, and lack of chemical reasoning capabilities.<n>We propose MPPReasoner, a multimodal large language model that incorporates chemical reasoning for molecular property prediction.
  arXiv  Detail & Related papers  (2025-10-11T15:05:45Z)
• NovoMolGen: Rethinking Molecular Language Model Pretraining [14.403924658046806]
  We introduce NovoMolGen, a family of transformer-based foundation models pretrained on 1.5 billion molecules for de-novo molecule generation.<n>Through extensive empirical analyses, we identify a weak correlation between performance metrics measured during pretraining and actual downstream performance.<n>NovoMolGen establishes new state-of-the-art results, substantially outperforming prior Mol-LLMs and specialized generative models in both unconstrained and goal-directed molecular generation tasks.
  arXiv  Detail & Related papers  (2025-08-19T00:04:48Z)
• Retrieval-based Controllable Molecule Generation [63.44583084888342]
  We propose a new retrieval-based framework for controllable molecule generation. We use a small set of molecules to steer the pre-trained generative model towards synthesizing molecules that satisfy the given design criteria. Our approach is agnostic to the choice of generative models and requires no task-specific fine-tuning.
  arXiv  Detail & Related papers  (2022-08-23T17:01:16Z)
• Deep Learning for Virtual Screening: Five Reasons to Use ROC Cost Functions [80.12620331438052]
  deep learning has become an important tool for rapid screening of billions of molecules in silico for potential hits containing desired chemical features. Despite its importance, substantial challenges persist in training these models, such as severe class imbalance, high decision thresholds, and lack of ground truth labels in some datasets. We argue in favor of directly optimizing the receiver operating characteristic (ROC) in such cases, due to its robustness to class imbalance.
  arXiv  Detail & Related papers  (2020-06-25T08:46:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.