# Accelerating scientific discovery with Co-Scientist

arXiv: https://arxiv.org/abs/2502.18864 · HTML: https://mlsanity.com/paper/2502.18864/

## Key facts

- Cited by 401 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 31 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## Builds on (most cited first, 3 of 3)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)

## Built on by (most cited first, 30 of 401)

- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review](https://mlsanity.com/paper/2504.19678/) (2025)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [Deep Research Agents: A Systematic Examination And Roadmap](https://mlsanity.com/paper/2506.18096/) (2025)
- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [AI-Researcher: Autonomous Scientific Innovation](https://mlsanity.com/paper/2505.18705/) (2025)
- [Kosmos: An AI Scientist for Autonomous Discovery](https://mlsanity.com/paper/2511.02824/) (2025)
- [ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents](https://mlsanity.com/paper/2511.07685/) (2025)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively](https://mlsanity.com/paper/2509.26603/) (2025)
- [SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?](https://mlsanity.com/paper/2507.05241/) (2025)
- [Building Production-Ready Probes For Gemini](https://mlsanity.com/paper/2601.11516/) (2026)
- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [Agentic Web: Weaving the Next Web with AI Agents](https://mlsanity.com/paper/2507.21206/) (2025)
- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [TxGemma: Efficient and Agentic LLMs for Therapeutics](https://mlsanity.com/paper/2504.06196/) (2025)
- [X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs](https://mlsanity.com/paper/2505.16997/) (2025)
- [ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks](https://mlsanity.com/paper/2508.15804/) (2025)
- [Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems](https://mlsanity.com/paper/2604.14228/) (2026)
- [A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers](https://mlsanity.com/paper/2508.21148/) (2025)
- [ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code](https://mlsanity.com/paper/2506.02314/) (2025)
- [NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents](https://mlsanity.com/paper/2510.07172/) (2025)
- [AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise](https://mlsanity.com/paper/2507.00310/) (2025)
- [MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research](https://mlsanity.com/paper/2503.13399/) (2025)
- [From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users](https://mlsanity.com/paper/2508.17281/) (2025)
- [CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization](https://mlsanity.com/paper/2504.04310/) (2025)
- [InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery](https://mlsanity.com/paper/2602.08990/) (2026)
- [When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research](https://mlsanity.com/paper/2505.11855/) (2025)
- [PaperBanana: Automating Academic Illustration for AI Scientists](https://mlsanity.com/paper/2601.23265/) (2026)

## 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.