# Large Language Model Agent for Modular Task Execution in Drug Discovery

arXiv: https://arxiv.org/abs/2507.02925 · HTML: https://mlsanity.com/paper/2507.02925/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 85 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [MolGAN: An implicit generative model for small molecular graphs](https://mlsanity.com/paper/1805.11973/) (2018)
- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing](https://mlsanity.com/paper/2007.06225/) (2020)
- [MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation](https://mlsanity.com/paper/2305.07508/) (2023)
- [CACTUS: Chemistry Agent Connecting Tool-Usage to Science](https://mlsanity.com/paper/2405.00972/) (2024)
- [PeptideBERT: A Language Model based on Transformers for Peptide Property Prediction](https://mlsanity.com/paper/2309.03099/) (2023)
- [Large Language Model Agent as a Mechanical Designer](https://mlsanity.com/paper/2404.17525/) (2024)
- [LLM-3D Print: Large Language Models To Monitor and Control 3D Printing](https://mlsanity.com/paper/2408.14307/) (2024)
- [MOFGPT: Generative Design of Metal-Organic Frameworks using Language Models](https://mlsanity.com/paper/2506.00198/) (2025)
- [Adsorb-Agent: Autonomous Identification of Stable Adsorption Configurations via Large Language Model Agent](https://mlsanity.com/paper/2410.16658/) (2024)
- [Multi-Peptide: Multimodality Leveraged Language-Graph Learning of Peptide Properties](https://mlsanity.com/paper/2407.03380/) (2024)
- [GradNav: Accelerated Exploration of Potential Energy Surfaces with Gradient-Based Navigation](https://mlsanity.com/paper/2403.10358/) (2024)

## Built on by (most cited first, 14 of 14)

- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [Agentic Additive Manufacturing Alloy Evaluation](https://mlsanity.com/paper/2510.02567/) (2025)
- [Polymer-Agent: Large Language Model Agent for Polymer Design](https://mlsanity.com/paper/2601.16376/) (2026)
- [Joint Optimization of Reasoning and Dual-Memory for Self-Learning Diagnostic Agent](https://mlsanity.com/paper/2604.07269/) (2026)
- [Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents](https://mlsanity.com/paper/2510.17491/) (2025)
- [Large Language Models Transform Organic Synthesis From Reaction Prediction to Automation](https://mlsanity.com/paper/2508.05427/) (2025)
- [Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agents](https://mlsanity.com/paper/2602.04813/) (2026)
- [CAi Copilot: Reducing Operational Workload in Molecular Design through Intent-Driven Agentic Workflows](https://mlsanity.com/paper/2608.06961/) (2026)
- [Meta-Learning for Cross-Task Generalization in Protein Mutation Property Prediction](https://mlsanity.com/paper/2510.20943/) (2025)
- [Model Gateway: Management Platform for Model-Driven Drug Discovery](https://mlsanity.com/paper/2512.05462/) (2025)
- [Domain Adapted Large Language Models for Additive Manufacturing](https://mlsanity.com/paper/2603.22017/) (2026)
- [Material Database Agent: A Multimodal Agentic Framework for Scientific Literature Mining](https://mlsanity.com/paper/2605.04278/) (2026)
- [Molecular LLM Agents: From Architectural Design to Scientific Autonomy](https://mlsanity.com/paper/2608.23104/) (2026)
- [From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?](https://mlsanity.com/paper/2610.06411/) (2026)

## Abstract (arXiv)

We present a modular framework powered by large language models (LLMs) that automates and streamlines key tasks across the early-stage computational drug discovery pipeline. By combining LLM reasoning with domain-specific tools, the framework performs biomedical data retrieval, literature-grounded question answering via retrieval-augmented generation, molecular generation, multi-property prediction, property-aware molecular refinement, and 3D protein-ligand structure generation. The agent autonomously retrieved relevant biomolecular information, including FASTA sequences, SMILES representations, and literature, and answered mechanistic questions with improved contextual accuracy compared to standard LLMs. It then generated chemically diverse seed molecules and predicted 75 properties, including ADMET-related and general physicochemical descriptors, which guided iterative molecular refinement. Across two refinement rounds, the number of molecules with QED > 0.6 increased from 34 to 55. The number of molecules satisfying empirical drug-likeness filters also rose; for example, compliance with the Ghose filter increased from 32 to 55 within a pool of 100 molecules. The framework also employed Boltz-2 to generate 3D protein-ligand complexes and provide rapid binding affinity estimates for candidate compounds. These results demonstrate that the approach effectively supports molecular screening, prioritization, and structure evaluation. Its modular design enables flexible integration of evolving tools and models, providing a scalable foundation for AI-assisted therapeutic discovery.