LearnA Survey on Autonomous Scientific Discovery
Surveys 38
A Survey of Progress, Challenges, and Future Directions
A Survey on Large Language Models in Scientific Discovery
Survey of research agents across literature, ideation, experimentation, and paper production.
Exploring the role of large language models in the scientific method: from hypothesis to discovery
From Equation Discovery to Autonomous Discovery Systems
A Survey of Artificial Intelligence for Scientific Research
A Survey on Large Language Models for Scientific Research
From Data Foundations to Agent Frontiers
A Survey of LLM-based Scientific Agents
A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation
A Comprehensive Survey of AI-Driven Research Support Systems
A Survey of AI Scientists and the Verification Gap
A Survey of Autonomous Research Agents
Systems, Methodologies, and Applications
A Creativity-Centered Survey
A Survey of Evaluation Tools for AI Assistants and Agents
A Survey of Capabilities, Challenges, and Future Directions
creating the engine for scientific discovery
Assistant, Collaborator, Scientist, and Evaluator
AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems
Execution Outcomes of LLM-Generated versus Human Research Ideas
Hidden Pitfalls of AI Scientist Systems
Lessons from Four Autonomous Research Attempts
Safety & Policy 20
prioritizing safeguarding over autonomy
A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
Benchmarking Safety Alignment on Six Scientific Domains
Toward Risk-Aware Scientific Discoveries by LLM Agents
Autonomous Scientific Exploration from a Baseline Paper
Dual-Use AI Challenge Benchmark and Scientific Refusal Tests
Consensus-based Recommendations for Machine-learning-based Science
arXiv CS now requires prior peer-review acceptance for surveys and position papers, citing LLM-driven volume.
Authors remain accountable for all content; reviewers may not share submissions with any language model.
A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists
Policies, Tools, and Practical Guidelines
A Large-Scale Dataset for Retraction Study
Tutorials & Talks 19
Gemini-powered coding agent that discovers new algorithms and improves known bounds.
Deployed impact across genomics, power grids, and quantum computing.
Multi-agent research partner, the lab write-up behind the Nature publication.
Reinforcement learning discovering faster matrix multiplication algorithms.
Hypothesis generation, computational discovery, literature insights, and science skills.
Official overview of the multi-agent hypothesis engine.
Structure prediction extended to proteins, nucleic acids, ligands, and ions.
An AI workbench for scientists, the closed reference point for open workbench efforts.
Connectors for Benchling, PubMed, and 10x, plus science-specific agent skills.
Free API credits for researchers running scientific workloads.
The Open Molecules 2025 (OMol25) Dataset, Evaluations, and Models
Agentic R&D platform, used to screen a non-PFAS datacenter coolant.
First large-scale foundation model of the atmosphere.
Related Lists 3
Broader reading list for agents in scientific discovery.
★ 99
Larger collection of AI Scientist papers, projects, and resources.
★ 16
Wider AI-for-Science papers and tools beyond autonomous research agents.
★ 1
Nothing matches those filters.