Automated research agents increasingly generate code, retrieve literature, and draft scientific artifacts, but they often fail to verify whether generated experiments execute correctly or whether cited sources support generated claims. We present AutoResearch, an execution-grounded multi-agent framework for reliable research workflow automation.
AutoResearch couples sandboxed Python/PyTorch execution, iterative code repair, citation verification, claim-support auditing, decision control, and structured \LaTeX{} artifact generation. The system treats runtime errors, citation-verification failures, and review-agent feedback as practical filtering signals for generated research artifacts.
In controlled evaluations on HumanEval, MBPP, a SciCode subset, citation-validation tasks, claim-support auditing, and small end-to-end workflow stress tests, AutoResearch improves execution success, citation validity, local claim support, and workflow completion relative to directly comparable baselines. Code-oriented agents are reported separately as partial comparisons.
It is important to note that AutoResearch is intended as a reliability-oriented research assistant, not as a fully autonomous scientist or a standalone manuscript-quality benchmark.
Source Code: GitHub - AutoResearch
Blogger's Review: The AutoResearch multi-agent framework demonstrates significant potential in the field of automated research, particularly in enhancing the reliability and validity of research outputs. By integrating code repair and literature verification techniques, this system provides researchers with a powerful tool for effective workflow management in complex research environments.