DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery

• URL: http://arxiv.org/abs/2505.13940v2
• Date: Mon, 28 Jul 2025 08:10:33 GMT
• Title: DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery
• Authors: Kun Li, Zhennan Wu, Shoupeng Wang, Jia Wu, Shirui Pan, Wenbin Hu,
• Abstract summary: Large language models (LLMs) integrated with autonomous agents hold significant potential for advancing scientific discovery through automated reasoning and task execution.<n>We introduce DrugPilot, a LLM-based agent system with a parameterized reasoning architecture designed for end-to-end scientific in drug discovery.<n>DrugPilot significantly outperforms state-of-the-art agents such as ReAct and LoT, achieving task completion rates of 98.0%, 93.5%, and 64.0% for simple, multi-tool, and multi-turn scenarios, respectively.
• Score: 54.79763887844838
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) integrated with autonomous agents hold significant potential for advancing scientific discovery through automated reasoning and task execution. However, applying LLM agents to drug discovery is still constrained by challenges such as large-scale multimodal data processing, limited task automation, and poor support for domain-specific tools. To overcome these limitations, we introduce DrugPilot, a LLM-based agent system with a parameterized reasoning architecture designed for end-to-end scientific workflows in drug discovery. DrugPilot enables multi-stage research processes by integrating structured tool use with a novel parameterized memory pool. The memory pool converts heterogeneous data from both public sources and user-defined inputs into standardized representations. This design supports efficient multi-turn dialogue, reduces information loss during data exchange, and enhances complex scientific decision-making. To support training and benchmarking, we construct a drug instruction dataset covering eight core drug discovery tasks. Under the Berkeley function-calling benchmark, DrugPilot significantly outperforms state-of-the-art agents such as ReAct and LoT, achieving task completion rates of 98.0%, 93.5%, and 64.0% for simple, multi-tool, and multi-turn scenarios, respectively. These results highlight DrugPilot's potential as a versatile agent framework for computational science domains requiring automated, interactive, and data-integrated reasoning.

Related papers

• DrugMCTS: a drug repurposing framework combining multi-agent, RAG and Monte Carlo Tree Search [10.123162419093973]
  DrugMCTS is a novel framework that integrates RAG, multi-agent collaboration, and Monte Carlo Tree Search for drug repositioning.<n>It employs five specialized agents tasked with retrieving and analyzing molecular and protein information, thereby enabling structured and iterative reasoning.<n>Our results highlight the importance of structured reasoning, agent-based collaboration, and feedback-driven search mechanisms.
  arXiv  Detail & Related papers  (2025-07-10T04:39:55Z)
• ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data [53.78763789036172]
  We present ChemActor, a fully fine-tuned large language model (LLM) as a chemical executor to convert between unstructured experimental procedures and structured action sequences.<n>This framework integrates a data selection module that selects data based on distribution divergence, with a general-purpose LLM, to generate machine-executable actions from a single molecule input.<n>Experiments on reaction-to-description (R2D) and description-to-action (D2A) tasks demonstrate that ChemActor achieves state-of-the-art performance, outperforming the baseline model by 10%.
  arXiv  Detail & Related papers  (2025-06-30T05:11:19Z)
• Deep Research Agents: A Systematic Examination And Roadmap [79.04813794804377]
  Deep Research (DR) agents are designed to tackle complex, multi-turn informational research tasks.<n>In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute DR agents.
  arXiv  Detail & Related papers  (2025-06-22T16:52:48Z)
• LLM Agent Swarm for Hypothesis-Driven Drug Discovery [2.7036595757881323]
  PharmaSwarm is a unified multi-agent framework that orchestrates specialized "agents" to propose, validate, and refine hypotheses for novel drug targets and lead compounds.<n>By acting as an AI copilot, PharmaSwarm can accelerate translational research and deliver high-confidence hypotheses more efficiently than traditional pipelines.
  arXiv  Detail & Related papers  (2025-04-24T22:27:50Z)
• PharmAgents: Building a Virtual Pharma with Large Language Model Agents [19.589707628042422]
  We introduce PharmAgents, a virtual pharmaceutical ecosystem driven by multi-agent collaboration.<n>The system integrates explainable, LLM-driven agents equipped with specialized machine learning models and computational tools.<n>It identifies potential therapeutic targets, discovers promising lead compounds, enhances binding affinity and key molecular properties, and performs in silico analyses of toxicity and synthetic feasibility.
  arXiv  Detail & Related papers  (2025-03-28T06:02:53Z)
• DatawiseAgent: A Notebook-Centric LLM Agent Framework for Automated Data Science [4.1431677219677185]
  DatawiseAgent is a notebook-centric agent framework that unifies interactions among user, agent and the computational environment.<n>It orchestrates four stages, including DSF-like planning, incremental execution, self-ging, and post-filtering.<n>It consistently outperforms or matches state-of-the-art methods across multiple model settings.
  arXiv  Detail & Related papers  (2025-03-10T08:32:33Z)
• RAG-Enhanced Collaborative LLM Agents for Drug Discovery [28.025359322895905]
  CLADD is a retrieval-augmented generation (RAG)-empowered agentic system tailored to drug discovery tasks.<n>We show that it outperforms general-purpose and domain-specific LLMs as well as traditional deep learning approaches.
  arXiv  Detail & Related papers  (2025-02-22T00:12:52Z)
• Empowering Large Language Models in Wireless Communication: A Novel Dataset and Fine-Tuning Framework [81.29965270493238]
  We develop a specialized dataset aimed at enhancing the evaluation and fine-tuning of large language models (LLMs) for wireless communication applications.<n>The dataset includes a diverse set of multi-hop questions, including true/false and multiple-choice types, spanning varying difficulty levels from easy to hard.<n>We introduce a Pointwise V-Information (PVI) based fine-tuning method, providing a detailed theoretical analysis and justification for its use in quantifying the information content of training data.
  arXiv  Detail & Related papers  (2025-01-16T16:19:53Z)
• DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration [24.65716292347949]
  DrugAgent is a multi-agent framework that automates machine learning (ML) programming for drug discovery tasks.<n>Our results show that DrugAgent consistently outperforms leading baselines.
  arXiv  Detail & Related papers  (2024-11-24T03:06:59Z)
• DrugAgent: Multi-Agent Large Language Model-Based Reasoning for Drug-Target Interaction Prediction [8.98329812378801]
  DrugAgent is a multi-agent system for drug-target interaction prediction.<n>It combines multiple specialized perspectives with transparent reasoning.<n>Our approach provides detailed, human-interpretable reasoning for each prediction.
  arXiv  Detail & Related papers  (2024-08-23T21:24:59Z)
• DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [50.36636396660163]
  We present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
  arXiv  Detail & Related papers  (2024-07-01T18:58:22Z)
• MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization [86.61052121715689]
  MatPlotAgent is a model-agnostic framework designed to automate scientific data visualization tasks. MatPlotBench is a high-quality benchmark consisting of 100 human-verified test cases.
  arXiv  Detail & Related papers  (2024-02-18T04:28:28Z)
• DrugAssist: A Large Language Model for Molecule Optimization [29.95488215594247]
  DrugAssist is an interactive molecule optimization model that performs optimization through human-machine dialogue. DrugAssist has achieved leading results in both single and multiple property optimization. We publicly release a large instruction-based dataset called MolOpt-Instructions for fine-tuning language models on molecule optimization tasks.
  arXiv  Detail & Related papers  (2023-12-28T10:46:56Z)
• Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration [71.95914457415624]
  Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. We propose an alternative formulation that leverages Multi-Agent RL (MARL) to tackle this problem. Our evaluation shows that the MARL formulation consistently outperforms single-agent RL baselines.
  arXiv  Detail & Related papers  (2022-11-29T17:10:24Z)
• ImDrug: A Benchmark for Deep Imbalanced Learning in AI-aided Drug Discovery [79.08833067391093]
  Real-world pharmaceutical datasets often exhibit highly imbalanced distribution. We introduce ImDrug, a benchmark with an open-source Python library which consists of 4 imbalance settings, 11 AI-ready datasets, 54 learning tasks and 16 baseline algorithms tailored for imbalanced learning. It provides an accessible and customizable testbed for problems and solutions spanning a broad spectrum of the drug discovery pipeline.
  arXiv  Detail & Related papers  (2022-09-16T13:35:57Z)
• SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target Affinity Prediction [127.43571146741984]
  Drug-Target Affinity (DTA) is of vital importance in early-stage drug discovery. wet experiments remain the most reliable method, but they are time-consuming and resource-intensive. Existing methods have primarily focused on developing techniques based on the available DTA data, without adequately addressing the data scarcity issue. We present the SSM-DTA framework, which incorporates three simple yet highly effective strategies.
  arXiv  Detail & Related papers  (2022-06-20T14:53:25Z)

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.