mlsanityData to 7 Oct 2026

Accelerating scientific discovery with Co-Scientist

arXiv 2502.18864 ↗First posted 26 Feb 2025cs.AI cs.CL cs.HCcited by 353

Not on the map. Why?

Cited by 154 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Scientific discovery is driven by scientists generating novel hypotheses for complex problems that undergo rigorous experimental validation. To augment this process, we introduce Co-Scientist, a multi-agent AI system built on Gemini for structured scientific thinking and hypothesis generation. Co-Scientist aims to help scientists discover new original knowledge. Conditioned on their research objectives and prior scientific evidence, it formulates demonstrably novel research hypotheses for experimental verification. The system's design involves agents continuously generating, critiquing and refining hypotheses accelerated by scaling test-time compute. Key contributions include: (1) a multi-agent architecture with an asynchronous task execution framework for flexible compute scaling; (2) a tournament evolution process for self-improving hypotheses generation. Automated evaluations show continued benefits of test-time compute scaling, improving hypothesis quality over time. While general purpose, we focus the validation in three biomedical applications: drug repurposing, novel target discovery, and explaining mechanisms of anti-microbial resistance. Specifically, Co-Scientist helped identify new drug repurposing candidates and synergistic combination therapies for acute myeloid leukemia, which were validated through in vitro experiments. These real-world validations demonstrate the potential of Co-Scientist to accelerate scientific discovery and usher in an era of AI empowered scientists.

Key facts. Cited by 353 papers in the map (data through 7 Oct 2026). Builds on 3 of its 31 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

3 of 31 references.

References · 3

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 255
  3. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 119; 2026: 234.

353 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchcited by 375
  3. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 146
  4. 2025Towards a Science of Scaling Agent Systemscited by 125
  5. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 122
  6. 2025Agentic Large Language Models, a surveycited by 105
  7. 2025AI-Researcher: Autonomous Scientific Innovationcited by 88
  8. 2025ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agentscited by 80
  9. 2025Kosmos: An AI Scientist for Autonomous Discoverycited by 78
  10. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  11. 2025DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressivelycited by 56
  12. 2025SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?cited by 45
38 more
  1. 2025Agentic Web: Weaving the Next Web with AI Agentscited by 43
  2. 2025TxGemma: Efficient and Agentic LLMs for Therapeuticscited by 40
  3. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  4. 2026Code as Agent Harnesscited by 40
  5. 2026Building Production-Ready Probes For Geminicited by 38
  6. 2025ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Codecited by 34
  7. 2025ReportBench: Evaluating Deep Research Agents via Academic Survey Taskscited by 34
  8. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 34
  9. 2025X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMscited by 33
  10. 2026Dive into Claude Code: The Design Space of Today's and Future AI Agent Systemscited by 33
  11. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Userscited by 32
  12. 2025NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agentscited by 32
  13. 2025MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Researchcited by 30
  14. 2025CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimizationcited by 28
  15. 2025AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprisecited by 28
  16. 2025When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Researchcited by 25
  17. 2026InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discoverycited by 24
  18. 2026AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaborationcited by 23
  19. 2025Sparks of Science: Hypothesis Generation Using Structured Paper Datacited by 22
  20. 2026PaperBanana: Automating Academic Illustration for AI Scientistscited by 22
  21. 2025AI Scientists Fail Without Strong Implementation Capabilitycited by 20
  22. 2026CooperBench: Why Coding Agents Cannot be Your Teammates Yetcited by 20
  23. 2025Code Researcher: Deep Research Agent for Large Systems Code and Commit Historycited by 19
  24. 2025InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scalingcited by 19
  25. 2025Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agentscited by 19
  26. 2026AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discoverycited by 17
  27. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 17
  28. 2025BrowseMaster: Towards Scalable Web Browsing via Tool-Augmented Programmatic Agent Paircited by 16
  29. 2025Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Researchcited by 16
  30. 2025Accelerating Scientific Discovery with Autonomous Goal-evolving Agentscited by 16
  31. 2026The Red Queen G"odel Machine: Co-Evolving Agents and Their Evaluatorscited by 16
  32. 2025How Far Are AI Scientists from Changing the World?cited by 15
  33. 2025OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientistscited by 15
  34. 2025A multi-agentic framework for real-time, autonomous freeform metasurface designcited by 14
  35. 2025Assessing the Chemical Intelligence of Large Language Modelscited by 14
  36. 2025Predicting Empirical AI Research Outcomes with Language Modelscited by 14
  37. 2025Trading-R1: Financial Trading with LLM Reasoning via Reinforcement Learningcited by 14
  38. 2025E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testingcited by 14

50 most cited of 353 All 353 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Accelerating Scientific Research with Gemini in the Real-World
  2. 2026HALO: Interactive Co-abductive Reasoning in Scientific Hypothesis Generation
  3. 2025AgentRxiv: Towards Collaborative Autonomous Research
  4. 2025Can AI Agents Design and Implement Drug Discovery Pipelines?
  5. 2025AI Agents in Drug Discovery
  6. 2026The Little Scientist: LLM Agent-Driven Discovery via the Scientific Method
  7. 2024DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents
  8. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery