Autonomous LLM-driven research from data to human-verifiable research papers

TL;DR

This paper presents an AI-driven platform that automates scientific research processes, generating verifiable research papers from data with minimal human intervention, demonstrating potential for accelerating discovery while maintaining scientific integrity.

Contribution

The authors developed 'data-to-paper', an automation platform enabling fully autonomous or semi-autonomous research workflows with traceability and human oversight, advancing AI's role in scientific discovery.

Findings

Autonomous generation of research papers from data with 80-90% accuracy for simple goals

Information-tracing ensures verifiability and transparency of generated research

Human oversight remains essential for complex research tasks

Abstract

As AI promises to accelerate scientific discovery, it remains unclear whether fully AI-driven research is possible and whether it can adhere to key scientific values, such as transparency, traceability and verifiability. Mimicking human scientific practices, we built data-to-paper, an automation platform that guides interacting LLM agents through a complete stepwise research process, while programmatically back-tracing information flow and allowing human oversight and interactions. In autopilot mode, provided with annotated data alone, data-to-paper raised hypotheses, designed research plans, wrote and debugged analysis codes, generated and interpreted results, and created complete and information-traceable research papers. Even though research novelty was relatively limited, the process demonstrated autonomous generation of de novo quantitative insights from data. For simple research goals, a fully-autonomous cycle can create manuscripts which recapitulate peer-reviewed publications without major errors in about 80-90%, yet as goal complexity increases, human co-piloting becomes critical for assuring accuracy. Beyond the process itself, created manuscripts too are inherently verifiable, as information-tracing allows to programmatically chain results, methods and data. Our work thereby demonstrates a potential for AI-driven acceleration of scientific discovery while enhancing, rather than jeopardizing, traceability, transparency and verifiability.