Awesome AI Scientist

Papers, systems, benchmarks, datasets and leaderboards for AI that does science.

499entries
400papers
328repositories
782kGitHub stars

Browse the cards Star on GitHub

Search/

sort

per row3

499 cards

The AI Scientist

The AI Scientist-v2

Agent Laboratory

AutoResearchClaw

CycleResearcher

Darwin Godel Machine

Kolb-Based Experiential Learning (Agent K)

CoI-Agent (Chain of Ideas)

SciMaster / X-Master

BioDiscoveryAgent

The AI Cosmologist

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers

Large Language Models for Automated Open-domain Scientific Hypotheses Discovery

Many Heads Are Better Than One

Literature Meets Data

AI Idea Bench 2025

Can Large Language Models Unlock Novel Scientific Research Ideas?

Sparks of Science

Large Language Models as Biomedical Hypothesis Generators

LDC: Learning to Generate Research Idea with Dynamic Control

TrustResearcher

Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas

ArxivDIGESTables

Patience is all you need! An agentic system for performing scientific literature review

Multi-Turn Agentic Scientific Literature Search via Workflow Induction

A Self-Improving Coding Agent

P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark

SciDoc2Diagrammer-MAF

Attribution in Scientific Literature

Do Language Models Know When They're Hallucinating References?

From Sparse to Dense

Can large language models provide useful feedback on research papers? A large-scale empirical analysis

LLMs Assist NLP Researchers

Monitoring AI-Modified Content at Scale

Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Review

When AI Co-Scientists Fail

AI-Assisted Peer Review at Scale

Gaming AI-Assisted Peer Reviews Poses New Risks to the Scientific Community

Unveiling the Merits and Defects of LLMs in Automatic Review Generation for Scientific Papers

Fact or Fiction

Agentic deep graph reasoning yields self-organizing knowledge networks

Experiences with Model Context Protocol Servers for Science and High Performance Computing

Mobile Robotic Chemist

Autonomous Mobile Robots for Exploratory Synthetic Chemistry

Multiagent-Driven Robotic AI Chemist

The World Avatar

DeepMind Tokamak Plasma Control

Scientific Generative Agent

DeepSeek-Prover

DeepSeek-Prover-V1.5

DeepSeek-Prover-V2

Goedel-Prover-V2

NuminaMath / AIMO Progress Prize

Equational Theories Project

Formal Conjectures

Generative Agents

Automated Social Science

LLM Agents Grounded in Self-Reports

Can Large Language Models Transform Computational Social Science?

Open Science Desktop

The Virtual Lab

STORM and Co-STORM

Local Deep Research

DeepResearchAgent

Deep Research from Scratch

Self-Driving Lab Demo

Scientific Agent Skills

create-research-experiment-repo

Virtual Scientists

Data Formulator

MetaGPT and Data Interpreter

autoresearch (karpathy)

ARIS (Auto-Research-In-Sleep)

AIRA / aira-dojo

DeepReview / DeepReviewer

ResearchCodeAgent

Materials Project

arXiv bulk data

Semantic Scholar Academic Graph API

PMC Open Access Subset

bioRxiv and medRxiv API

OpenReview API v2

Papers with Code successor

Open Reaction Database

Materials Cloud

CrystaLLM training data

AlphaFold Protein Structure Database

European Nucleotide Archive

CELLxGENE Discover

NASA Exoplanet Archive

Harvard Dataverse

ScienceAgentBench

The Automated LLM Speedrunning Benchmark

ResearchCodeBench

SciReplicate-Bench

ReplicationBench

ReplicatorBench

DeepScholar-Bench

AutoResearchBench

LitReview Arena

CoCoReviewBench

ResearchBench (Liu et al.)

Humanity's Last Exam

LabSafety Bench

Matbench Discovery

HAL: Holistic Agent Leaderboard

ResearchClawBench

METR evaluations

Epoch AI Benchmarking Hub

Papers With Code (shut down)

From AI for Science to Agentic Science

Agentic AI for Scientific Discovery

From Automation to Autonomy

Agent Systems for Academic Research Automation

Exploring the role of LLMs in the scientific method

Automated Scientific Discovery

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery

A Survey of Scientific Large Language Models

Towards Scientific Intelligence

Transforming Science with Large Language Models

From Hypothesis to Publication

A Survey of AI Scientists

Autonomous Research Agents

A Comprehensive Survey of Deep Research

A Survey on Hypothesis Generation for Scientific Discovery in the Era of Large Language Models

Large Language Models for Scientific Idea Generation

A review of large language models and autonomous agents in chemistry

A Survey on Large Language Model-based Agents for Statistics and Data Science

Measuring Data Science Automation

LLM-Based Data Science Agents

The rise of self-driving labs in chemical and materials sciences

Empowering biomedical discovery with AI agents

Nobel Turing Challenge

Exploring the use of AI authors and reviewers at Agents4Science

Evolving Roles of LLMs in Scientific Innovation

Scaling Laws in Scientific Discovery with AI and Robot Scientists

The Ideation-Execution Gap

Can AI make scientific discoveries?

The More You Automate, the Less You See

Why LLMs Aren't Scientists Yet

AI Research Agents Narrow Scientific Exploration

Can AI agents conduct open-ended AI research? Early evidence from two case studies

How Far Are AI Scientists from Changing the World?

Fully Autonomous AI Agents Should Not be Developed

Risks of AI scientists

Benchmarking large language models on safety risks in scientific laboratories

Control Risk for Potential Misuse of Artificial Intelligence in Science

Dual use of artificial-intelligence-powered drug discovery

Jr. AI Scientist and Its Risk Report

Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models

LLM Novice Uplift on Dual-Use, In Silico Biology Tasks

Forbidden Science

Leakage and the Reproducibility Crisis in ML-based Science

arXiv policy update for review articles and position papers in cs

NeurIPS 2025 Policy on the Use of Large Language Models

ChatGPT is fun, but not an author

Tools such as ChatGPT threaten transparent science; here are our ground rules for their use

AI-Generated Figures in Academic Publishing

Google DeepMind, AlphaEvolve

Google DeepMind, AlphaEvolve one year on

Google DeepMind, Co-Scientist

Google DeepMind, AlphaTensor

Google, Gemini for Science

Google Research, AI co-scientist

Google DeepMind and Isomorphic Labs, AlphaFold 3

Anthropic, Claude Science

Anthropic, Claude for Life Sciences

Anthropic, AI for Science Program

Meta FAIR, OMol25 and fairchem

Microsoft, Discovery

Microsoft Research, Aurora

Which "AI scientist" suits your lab? A guide for the perplexed

AI scientist agents violate research integrity rules

How to build an AI scientist, first peer-reviewed paper spills the secrets

The AI co-scientist is here

Disruption of the research software landscape through AI software generation

Engineering AI co-scientists for statistical genetics applications

awesome-agents4science

The Library of AI Scientist

AI4Science reading list