# BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments

arXiv: https://arxiv.org/abs/2405.17631 · HTML: https://mlsanity.com/paper/2405.17631/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 19 of its 122 references that are in the map.
- First posted on arXiv 27 May 2024.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- 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)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [PaperQA: Retrieval-Augmented Generative Agent for Scientific Research](https://mlsanity.com/paper/2312.07559/) (2023)
- [Large Language Models to Enhance Bayesian Optimization](https://mlsanity.com/paper/2402.03921/) (2024)
- [Empowering Biomedical Discovery with AI Agents](https://mlsanity.com/paper/2404.02831/) (2024)
- [GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information](https://mlsanity.com/paper/2304.09667/) (2023)
- [Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective](https://mlsanity.com/paper/2306.06615/) (2023)
- [CRISPR-GPT for Agentic Automation of Gene-editing Experiments](https://mlsanity.com/paper/2404.18021/) (2024)
- [FIRST: A Framework for Optimizing Information Quality in Mobile Crowdsensing Systems](https://mlsanity.com/paper/1804.11147/) (2018)
- [Zero-Shot Clinical Trial Patient Matching with LLMs](https://mlsanity.com/paper/2402.05125/) (2024)
- [ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback](https://mlsanity.com/paper/2305.18090/) (2023)
- [GeneDisco: A Benchmark for Experimental Design in Drug Discovery](https://mlsanity.com/paper/2110.11875/) (2021)
- [Evaluation of large language models for discovery of gene set function](https://mlsanity.com/paper/2309.04019/) (2023)
- [DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design](https://mlsanity.com/paper/2312.04064/) (2023)
- [Comparative Performance Evaluation of Large Language Models for Extracting Molecular Interactions and Pathway Knowledge](https://mlsanity.com/paper/2307.08813/) (2023)

## Built on by (most cited first, 30 of 53)

- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents](https://mlsanity.com/paper/2503.24047/) (2025)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities](https://mlsanity.com/paper/2409.11654/) (2024)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [A Survey on the Optimization of Large Language Model-based Agents](https://mlsanity.com/paper/2503.12434/) (2025)
- [DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration](https://mlsanity.com/paper/2411.15692/) (2024)
- [RAG-Enhanced Collaborative LLM Agents for Drug Discovery](https://mlsanity.com/paper/2502.17506/) (2025)
- [How Far Are AI Scientists from Changing the World?](https://mlsanity.com/paper/2507.23276/) (2025)
- [LLMs for Bayesian Optimization in Scientific Domains: Are We There Yet?](https://mlsanity.com/paper/2509.21403/) (2025)
- [HeurekaBench: A Benchmarking Framework for AI Co-scientist](https://mlsanity.com/paper/2601.01678/) (2026)
- [From Question Answering to Task Completion: A Survey on Agent System and Harness Design](https://mlsanity.com/paper/2606.20683/) (2026)
- [Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics](https://mlsanity.com/paper/2510.09901/) (2025)
- [BioMaze: Benchmarking and Enhancing Large Language Models for Biological Pathway Reasoning](https://mlsanity.com/paper/2502.16660/) (2025)
- [Contextualizing biological perturbation experiments through language](https://mlsanity.com/paper/2502.21290/) (2025)
- [Pathology-CoT: Learning Visual Chain-of-Thought Agent from Expert Whole Slide Image Diagnosis Behavior](https://mlsanity.com/paper/2510.04587/) (2025)
- [DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking](https://mlsanity.com/paper/2605.26087/) (2026)
- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [BioDSA-1K: Benchmarking Data Science Agents for Biomedical Research](https://mlsanity.com/paper/2505.16100/) (2025)
- [JoyAgent-JDGenie: Technical Report on the GAIA](https://mlsanity.com/paper/2510.00510/) (2025)
- [MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback](https://mlsanity.com/paper/2505.17873/) (2025)
- [K-Dense Analyst: Towards Fully Automated Scientific Analysis](https://mlsanity.com/paper/2508.07043/) (2025)
- [Agentic Exploration of Physics Models](https://mlsanity.com/paper/2509.24978/) (2025)
- [Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition](https://mlsanity.com/paper/2510.15280/) (2025)
- [ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity](https://mlsanity.com/paper/2606.11150/) (2026)
- [The Curious Language Model: Strategic Test-Time Information Acquisition](https://mlsanity.com/paper/2506.09173/) (2025)
- [Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives](https://mlsanity.com/paper/2506.09656/) (2025)
- [IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared Spectra](https://mlsanity.com/paper/2508.16112/) (2025)
- [What can large language models do for sustainable food?](https://mlsanity.com/paper/2503.04734/) (2025)

## Abstract (arXiv)

Agents based on large language models have shown great potential in accelerating scientific discovery by leveraging their rich background knowledge and reasoning capabilities. In this paper, we introduce BioDiscoveryAgent, an agent that designs new experiments, reasons about their outcomes, and efficiently navigates the hypothesis space to reach desired solutions. We demonstrate our agent on the problem of designing genetic perturbation experiments, where the aim is to find a small subset out of many possible genes that, when perturbed, result in a specific phenotype (e.g., cell growth). Utilizing its biological knowledge, BioDiscoveryAgent can uniquely design new experiments without the need to train a machine learning model or explicitly design an acquisition function as in Bayesian optimization. Moreover, BioDiscoveryAgent, using Claude 3.5 Sonnet, achieves an average of 21% improvement in predicting relevant genetic perturbations across six datasets, and a 46% improvement in the harder task of non-essential gene perturbation, compared to existing Bayesian optimization baselines specifically trained for this task. Our evaluation includes one dataset that is unpublished, ensuring it is not part of the language model's training data. Additionally, BioDiscoveryAgent predicts gene combinations to perturb more than twice as accurately as a random baseline, a task so far not explored in the context of closed-loop experiment design. The agent also has access to tools for searching the biomedical literature, executing code to analyze biological datasets, and prompting another agent to critically evaluate its predictions. Overall, BioDiscoveryAgent is interpretable at every stage, representing an accessible new paradigm in the computational design of biological experiments with the potential to augment scientists' efficacy.