# Kosmos: An AI Scientist for Autonomous Discovery arXiv: https://arxiv.org/abs/2511.02824 ยท HTML: https://mlsanity.com/paper/2511.02824/ ## Key facts - Cited by 92 papers in the map (data through 14 Oct 2026). - Placed in World models for language agents, one of 11 directions in World models. - Builds on 7 of its 58 references that are in the map. - First posted on arXiv 4 Nov 2025. ## Placed in - World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/) ## Builds on (most cited first, 7 of 7) - [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024) - [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025) - [Measuring AI Ability to Complete Long Software Tasks](https://mlsanity.com/paper/2503.14499/) (2025) - [Language agents achieve superhuman synthesis of scientific knowledge](https://mlsanity.com/paper/2409.13740/) (2024) - [BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology](https://mlsanity.com/paper/2503.00096/) (2025) - [Robin: A multi-agent system for automating scientific discovery](https://mlsanity.com/paper/2505.13400/) (2025) - [Problems with classification, hypothesis testing, and estimator convergence in the analysis of degree distributions in networks](https://mlsanity.com/paper/2003.14012/) (2020) ## Built on by (most cited first, 30 of 92) - [CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution](https://mlsanity.com/paper/2512.23880/) (2025) - [Towards Execution-Grounded Automated AI Research](https://mlsanity.com/paper/2601.14525/) (2026) - [InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery](https://mlsanity.com/paper/2602.08990/) (2026) - [Accelerating Scientific Discovery with Autonomous Goal-evolving Agents](https://mlsanity.com/paper/2512.21782/) (2025) - [Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper](https://mlsanity.com/paper/2511.04583/) (2025) - [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026) - [AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery](https://mlsanity.com/paper/2605.23204/) (2026) - [Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries](https://mlsanity.com/paper/2606.10402/) (2026) - [Simple Baselines are Competitive with Code Evolution](https://mlsanity.com/paper/2602.16805/) (2026) - [AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation](https://mlsanity.com/paper/2605.28655/) (2026) - [Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale](https://mlsanity.com/paper/2512.20469/) (2025) - [El Agente Quntur: A research collaborator agent for quantum chemistry](https://mlsanity.com/paper/2602.04850/) (2026) - [Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery](https://mlsanity.com/paper/2605.08956/) (2026) - [Towards autonomous quantum physics research using LLM agents with access to intelligent tools](https://mlsanity.com/paper/2511.11752/) (2025) - [Principle-Evolvable Scientific Discovery via Uncertainty Minimization](https://mlsanity.com/paper/2602.06448/) (2026) - [CREATE: Testing LLMs for Associative Creativity](https://mlsanity.com/paper/2603.09970/) (2026) - [PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research](https://mlsanity.com/paper/2604.15411/) (2026) - [Unlocking LLM Creativity in Science through Analogical Reasoning](https://mlsanity.com/paper/2605.11258/) (2026) - [Harnessing AtomisticSkills for Agentic Atomistic Research](https://mlsanity.com/paper/2605.24002/) (2026) - [SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discovery](https://mlsanity.com/paper/2602.09132/) (2026) - [El Agente Gr'afico: A Semantic Execution Runtime for Scientific Agents](https://mlsanity.com/paper/2602.17902/) (2026) - [Sanity Checks for Agentic Data Science](https://mlsanity.com/paper/2604.11003/) (2026) - [From AGI to ASI](https://mlsanity.com/paper/2606.12683/) (2026) - [ASI-Bench: At the Dawn of Artificial Superintelligence](https://mlsanity.com/paper/2608.17271/) (2026) - [ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments](https://mlsanity.com/paper/2609.19134/) (2026) - [MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models](https://mlsanity.com/paper/2512.21231/) (2025) - [Towards LLM-enabled autonomous combustion research: A literature-aware agent for self-corrective modeling workflows](https://mlsanity.com/paper/2601.01357/) (2026) - [Clever Materials: When Models Identify Good Materials for the Wrong Reasons](https://mlsanity.com/paper/2602.17730/) (2026) - [ResearchEnvBench: Benchmarking Agents on Environment Synthesis for Research Code Execution](https://mlsanity.com/paper/2603.06739/) (2026) - [CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad](https://mlsanity.com/paper/2603.14575/) (2026) ## Abstract (arXiv) Data-driven scientific discovery requires iterative cycles of literature search, hypothesis generation, and data analysis. Substantial progress has been made towards AI agents that can automate scientific research, but all such agents remain limited in the number of actions they can take before losing coherence, thus limiting the depth of their findings. Here we present Kosmos, an AI scientist that automates data-driven discovery. Given an open-ended objective and a dataset, Kosmos runs for up to 12 hours performing cycles of parallel data analysis, literature search, and hypothesis generation before synthesizing discoveries into scientific reports. Unlike prior systems, Kosmos uses a structured world model to share information between a data analysis agent and a literature search agent. The world model enables Kosmos to coherently pursue the specified objective over 200 agent rollouts, collectively executing an average of 42,000 lines of code and reading 1,500 papers per run. Kosmos cites all statements in its reports with code or primary literature, ensuring its reasoning is traceable. Independent scientists found 79.4% of statements in Kosmos reports to be accurate, and collaborators reported that a single 20-cycle Kosmos run performed the equivalent of 6 months of their own research time on average. Furthermore, collaborators reported that the number of valuable scientific findings generated scales linearly with Kosmos cycles (tested up to 20 cycles). We highlight seven discoveries made by Kosmos that span metabolomics, materials science, neuroscience, and statistical genetics. Three discoveries independently reproduce findings from preprinted or unpublished manuscripts that were not accessed by Kosmos at runtime, while four make novel contributions to the scientific literature.