AI Agents for Scientific Discovery

Follow this topic Ask about this topic

AI agents for scientific discovery aim to help researchers move from questions and hypotheses to analysis, experiments, and evidence-backed conclusions. Common approaches combine language models with literature retrieval, code execution, scientific simulators, laboratory instruments, and specialized agents in iterative hypothesis–test–revision loops. Work spans fields such as materials science, biology, physics, chemistry, and mathematics, with systems also developing reusable skills and memories to build on prior results. A central challenge is ensuring that promising outputs are genuinely novel, scientifically valid, reproducible, and grounded in evidence, especially in long workflows and physical experiments.

Latest papers

288 papers57 papers in the last four weeks, up 111% on the four weeks before. 0.3% of all new papers.

Mozi: Governed Autonomy for Drug Discovery LLM Agents
Mar 4, 2026He Cao, Siyu Liu, Fan Zhang +7AI Agents for Scientific Discovery LLM Agent Orchestration
SciDER: Scientific Data-centric End-to-end Researcher
Mar 2, 2026Ke Lin, Owais Aijaz, Yilin Lu +3AI Agents for Scientific Discovery Scientific Workflow Automation
Data Science, College of William & Mary, Williamsburg, USA · Natural Language Processing, MBZUAI, Abu Dhabi, UAE · Computer Science, University of Minnesota, Minneapolis, USA +1
Agentic Exploration of PDE Spaces using Latent Foundation Models for Parameterized Simulations
Feb 26, 2026Abhijeet Vishwasrao, Francisco Giral, Mahmoud Golestanian +8AI Agents for Scientific Discovery Physics-Based Simulation
University of Michigan · Universidad Polit´ecnica de Madrid · Purdue University +3
ArchAgent: Agentic AI-driven Computer Architecture Discovery
Feb 25, 2026Raghav Gupta, Akanksha Jain, Abraham Gonzalez +10Automated Algorithm Discovery AI Agents for Scientific Discovery
University of California, Berkeley · Google · Google DeepMind
Grounding LLMs in Scientific Discovery via Embodied Actions
Feb 24, 2026Bo Zhang, Jinfeng Zhou, Yuxuan Chen +3AI Agents for Scientific Discovery LLM Grounding
Tsinghua University, Beijing, China.
From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Science
Feb 23, 2026Lukas Weidener, Marko Brkić, Phillip Lee +3Autonomous Research Agents AI Agents for Scientific Discovery
Are LLMs Ready for Neural-integrated Mechanistic Modeling? A Benchmark and Agentic Framework
Feb 20, 2026Zihan Guan, Rituparna Datta, Mengxuan Hu +5Large Language Model-Guided Scientific Discovery AI Agents for Scientific Discovery
University of Virginia
El Agente Gráfico: A Semantic Execution Runtime for Scientific Agents
Feb 19, 2026Jiaru Bai, Abdulrahman Aldossary, Thomas Swanick +12Computational Quantum Chemistry Runtime Enforcement for AI Agents
Department of Chemistry, University of Toronto, 80 St. George St., Toronto, ON M5S 3H6, Canada · Vector Institute for Artificial Intelligence, W1140-108 College St., Schwartz Reisman Innovation Campus, Toronto, ON M5G 0C6, Canada · Department of Computer Science, University of Toronto, 40 St George St., Toronto, ON M5S 2E4, Canada +10
AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing
Feb 19, 2026Jianda Du, Youran Sun, Haizhao YangPDE Solving Automated Algorithm Discovery
Department of Mathematics, University of Maryland, College Park, MD, USA · Department of Computer Science, University of Maryland, College Park, MD, USA
PeroMAS: A Multi-agent System of Perovskite Material Discovery
Feb 10, 2026Yishu Wang, Wei Liu, Yifan Li +8Multi-Agent LLM Systems AI Agents for Scientific Discovery
Southeast University Nanjing, China · Sun Yat-Sen University Zhuhai, China · The Hong Kong University of Science and Technology Hong Kong, China +2
El Agente Quntur: A research collaborator agent for quantum chemistry
Feb 4, 2026Juan B. Pérez-Sánchez, Yunheng Zou, Jorge A. Campos-Gonzalez-Angulo +12AI Agents for Scientific Discovery Computational Quantum Chemistry
Department of Chemistry, University of Toronto, 80 St. George St., Toronto, ON M5S 3H6, Canada · Vector Institute for Artificial Intelligence, W1140-108 College St., Schwartz Reisman Innovation Campus, Toronto, ON M5G 0C6, Canada · Acceleration Consortium, 700 University Ave., Toronto, ON M7A 2S4, Canada +6
AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.org
Dec 12, 2025Jaehyung Lee, Justin Ely, Kent Zhang +3AI Agents for Scientific Discovery LLM Agent Evaluation
Department of Materials Science and Engineering, Johns Hopkins University, Baltimore, MD 21218, USA · Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218, USA · Department of Physics and Astronomy, West Virginia University, Morgantown, WV 26506, USA
Multi-Agent Design Assistant for the Simulation of Inertial Fusion Energy
Oct 2, 2025Meir H. Shachar, Dane M. Sterbentz, Harshitha Menon +10Multiphysics Simulation Multi-Agent LLM Systems
Lawrence Livermore National Laboratory Livermore, CA, USA · Lawrence Livermore National Laboratory Livermore, CA 94550, USA · Sandia National Laboratories Albuquerque, NM, USA +3
Speak to a Protein: An Interactive Multimodal Co-Scientist
Oct 1, 2025Carles Navarro, Mariona Torrens, Philipp Thölke +2AI Agents for Scientific Discovery Scientific QA
Acellera Labs, C/ Doctor Trueta 183, 08005 Barcelona, Spain · Computational Science Laboratory, Universitat Pompeu Fabra, PRBB, C/ Doctor Aiguader 88, 08003 Barcelona, Spain · Instituci´o Catalana de Recerca i Estudis Avan¸cats (ICREA), Passeig Llu´ıs Companys 23, 08010 Barcelona, Spain
Agentic Exploration of Physics Models
Sep 29, 2025Maximilian Nägele, Florian MarquardtAI Agents for Scientific Discovery Scientific Discovery
Max Planck Institute for the Science of Light, Staudtstraße 2, 91058 Erlangen, Germany · Department of Physics, Friedrich-Alexander Universität Erlangen-Nürnberg, Staudtstraße 5, 91058 Erlangen, Germany
AI Scientists for Building Virtual-Cell Models
Aug 4, 2025Xiangru Tang, Jiapeng Chen, Daniel Shao +12AI Agents for Scientific Discovery Autonomous Research Agents
Yale University · University of Pennsylvania · Helmholtz Zentrum München +3
GenoMAS: Guided Multi-Agent Programming for Scientific Discovery from Genomic Data
Jul 28, 2025Haoyang Liu, Yijiang Li, Haohan WangAI Agents for Scientific Discovery Data Analysis Agents
University of Illinois at Urbana-Champaign · University of California, San Diego
Neural Architecture Discovery via Autonomous Evolution
Jul 24, 2025Weixian Xu, Yixiu Liu, Yang Nan +4Autonomous Research Agents AI Agents for Scientific Discovery
Shanghai Jiao Tong University · SII · GAIR +1

Mar 4, 2026J/K move · Enter open · S save

Mozi: Governed Autonomy for Drug Discovery LLM Agents

He Cao, Siyu Liu, Fan Zhang, Zijing Liu+6

AI Agents for Scientific Discovery LLM Agent Orchestration Long-Horizon LLM Agents AI Agent Governance Drug Discovery

Open paper AskPDF arXiv

Tool-augmented large language model (LLM) agents promise to unify scientific reasoning with computation, yet their deployment in high-stakes domains like drug discovery is bottlenecked by two critical barriers: unconstrained tool-use governance and poor long-horizon reliability. In dependency-heavy pharmaceutical pipelines, autonomous agents often drift into irreproducible trajectories, where early-stage hallucinations multiplicatively compound into downstream failures. To overcome this, we present Mozi, a dual-layer architecture that bridges the flexibility of generative AI with the deterministic rigor of computational biology. Layer A (Control Plane) establishes a governed supervisor--worker hierarchy that enforces role-based tool isolation, limits execution to constrained action spaces, and drives reflection-based replanning. Layer B (Workflow Plane) operationalizes canonical drug discovery stages -- from Target Identification to Lead Optimization -- as stateful, composable skill graphs. This layer integrates strict data contracts and strategic human-in-the-loop (HITL) checkpoints to safeguard scientific validity at high-uncertainty decision boundaries. Operating on the design principle of ``free-form reasoning for safe tasks, structured execution for long-horizon pipelines,'' Mozi provides built-in robustness mechanisms and trace-level audibility to completely mitigate error accumulation. We evaluate Mozi on PharmaBench, a curated benchmark for biomedical agents, demonstrating superior orchestration accuracy over existing baselines. Furthermore, through end-to-end therapeutic case studies, we demonstrate Mozi's ability to navigate massive chemical spaces, enforce stringent toxicity filters, and generate highly competitive in silico candidates, effectively transforming the LLM from a fragile conversationalist into a reliable, governed co-scientist.