AgentRxiv: Towards Collaborative Autonomous Research
Preprint
Abstract
Progress in scientific discovery is rarely the result of a single "Eureka" moment, but is rather the product of hundreds of scientists incrementally working together toward a common goal. While existing agent workflows are capable of producing research autonomously, they do so in isolation, without the ability to continuously improve upon prior research results. To address these challenges, we introduce AgentRxiv-a framework that lets LLM agent laboratories upload and retrieve reports from a shared preprint server in order to collaborate, share insights, and iteratively build on each other's research. We task agent laboratories to develop new reasoning and prompting techniques and find that agents with access to their prior research achieve higher performance improvements compared to agents operating in isolation (11.4% relative improvement over baseline on MATH-500). We find that the best performing strategy generalizes to benchmarks in other domains (improving on average by 3.3%). Multiple agent laboratories sharing research through AgentRxiv are able to work together towards a common goal, progressing more rapidly than isolated laboratories, achieving higher overall accuracy (13.7% relative improvement over baseline on MATH-500). These findings suggest that autonomous agents may play a role in designing future AI systems alongside humans. We hope that AgentRxiv allows agents to collaborate toward research goals and enables researchers to accelerate discovery.Keywords
All Related Versions
This publication has 54 references indexed in Scilit:
- LUMI-lab: A foundation model-driven autonomous platform enabling discovery of ionizable lipid designs for mRNA deliveryCell, 2026
- Tool learning with large language models: a surveyFrontiers of Computer Science, 2025
- SciAgents: Automating Scientific Discovery Through Bioinspired Multi‐Agent Intelligent Graph ReasoningAdvanced Materials, 2024
- Large language models surpass human experts in predicting neuroscience resultsNature Human Behaviour, 2024
- Mathematical discoveries from program search with large language modelsNature, 2023
- Can ChatGPT be an author? A study of artificial intelligence authorship policies in top academic journalsLearned Publishing, 2023
- Discovering faster matrix multiplication algorithms with reinforcement learningNature, 2022
- Advancing mathematics by guiding human intuition with AINature, 2021
- Highly accurate protein structure prediction with AlphaFoldNature, 2021
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in positionBiological Cybernetics, 1980