# AIGS: Generating Science from AI-Powered Automated Falsification

arXiv: https://arxiv.org/abs/2411.11910 · HTML: https://mlsanity.com/paper/2411.11910/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 110 references that are in the map.
- First posted on arXiv 17 Nov 2024.

## Builds on (most cited first, 30 of 43)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery](https://mlsanity.com/paper/2410.05080/) (2024)
- [Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents](https://mlsanity.com/paper/2405.02957/) (2024)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [ART: Automatic multi-step reasoning and tool-use for large language models](https://mlsanity.com/paper/2303.09014/) (2023)
- [Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews](https://mlsanity.com/paper/2403.07183/) (2024)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [LLM Critics Help Catch LLM Bugs](https://mlsanity.com/paper/2407.00215/) (2024)
- [War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars](https://mlsanity.com/paper/2311.17227/) (2023)
- [MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution](https://mlsanity.com/paper/2403.17927/) (2024)
- [LLM-SR: Scientific Equation Discovery via Programming with Large Language Models](https://mlsanity.com/paper/2404.18400/) (2024)
- [DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?](https://mlsanity.com/paper/2409.07703/) (2024)
- [Mapping the Increasing Use of LLMs in Scientific Papers](https://mlsanity.com/paper/2404.01268/) (2024)
- [MARG: Multi-Agent Review Generation for Scientific Papers](https://mlsanity.com/paper/2401.04259/) (2024)
- [DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents](https://mlsanity.com/paper/2406.06769/) (2024)
- [AgentReview: Exploring Peer Review Dynamics with LLM Agents](https://mlsanity.com/paper/2406.12708/) (2024)
- [Hypothesis Generation with Large Language Models](https://mlsanity.com/paper/2404.04326/) (2024)
- [Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System](https://mlsanity.com/paper/2410.09403/) (2024)
- [MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents](https://mlsanity.com/paper/2408.14033/) (2024)

## Built on by (most cited first, 18 of 18)

- [Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents](https://mlsanity.com/paper/2503.24047/) (2025)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [AI Scientists Fail Without Strong Implementation Capability](https://mlsanity.com/paper/2506.01372/) (2025)
- [How Far Are AI Scientists from Changing the World?](https://mlsanity.com/paper/2507.23276/) (2025)
- [CellForge: Agentic Design of Virtual Cell Models](https://mlsanity.com/paper/2508.02276/) (2025)
- [A Survey of AI Scientists](https://mlsanity.com/paper/2510.23045/) (2025)
- [AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery](https://mlsanity.com/paper/2605.23204/) (2026)
- [Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator](https://mlsanity.com/paper/2507.11810/) (2025)
- [From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems](https://mlsanity.com/paper/2503.01424/) (2025)
- [Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists](https://mlsanity.com/paper/2604.28158/) (2026)
- [Can AI Validate Science? Benchmarking LLMs for Accurate Scientific Claim rightarrow Evidence Reasoning](https://mlsanity.com/paper/2506.08235/) (2025)
- [S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research](https://mlsanity.com/paper/2602.01550/) (2026)
- [Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents](https://mlsanity.com/paper/2607.09195/) (2026)
- [From AutoRecSys to AutoRecLab: A Call to Build, Evaluate, and Govern Autonomous Recommender-Systems Research Labs](https://mlsanity.com/paper/2510.18104/) (2025)
- [The Greatness of Science Cannot Be Planned: Agentic Auto-Research is Fuzz Testing](https://mlsanity.com/paper/2608.09855/) (2026)
- [EvoMU: Evolutionary Machine Unlearning](https://mlsanity.com/paper/2602.02139/) (2026)
- [Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems](https://mlsanity.com/paper/2608.14667/) (2026)
- [Verify Less, Evolve More: Training Idea-Level Critics for Verification-Efficient ML Evolving Agents](https://mlsanity.com/paper/2610.08993/) (2026)

## Abstract (arXiv)

Rapid development of artificial intelligence has drastically accelerated the development of scientific discovery. Trained with large-scale observation data, deep neural networks extract the underlying patterns in an end-to-end manner and assist human researchers with highly-precised predictions in unseen scenarios. The recent rise of Large Language Models (LLMs) and the empowered autonomous agents enable scientists to gain help through interaction in different stages of their research, including but not limited to literature review, research ideation, idea implementation, and academic writing. However, AI researchers instantiated by foundation model empowered agents with full-process autonomy are still in their infancy. In this paper, we study AI-Generated Science (AIGS), where agents independently and autonomously complete the entire research process and discover scientific laws. By revisiting the definition of scientific research, we argue that textitfalsification is the essence of both human research process and the design of an AIGS system. Through the lens of falsification, prior systems attempting towards AI-Generated Science either lack the part in their design, or rely heavily on existing verification engines that narrow the use in specialized domains. In this work, we propose Baby-AIGS as a baby-step demonstration of a full-process AIGS system, which is a multi-agent system with agents in roles representing key research process. By introducing FalsificationAgent, which identify and then verify possible scientific discoveries, we empower the system with explicit falsification. Experiments on three tasks preliminarily show that Baby-AIGS could produce meaningful scientific discoveries, though not on par with experienced human researchers. Finally, we discuss on the limitations of current Baby-AIGS, actionable insights, and related ethical issues in detail.