Tag
Interview discussing infrastructure for auto-research using DAGs, including how agents can execute DAGs and how to build large public DAGs.
AutoResearchClaw is a GitHub repository that automates the entire AI research pipeline from an idea to a full conference paper with real experiments, verified citations, and working code, outperforming previous autonomous research systems by 54.7% on a 55-topic benchmark.
This paper introduces ResearchArena, a scaffold for evaluating auto-research agents, and finds that while agent-generated papers appear competitive under manuscript-only review, artifact-aware review reveals severe failures in experimental rigor, with no paper meeting top-tier acceptance standards.
This paper introduces an auto-research framework using specialist agents to iteratively refine training recipes through an empirical loop of code execution and feedback. The system autonomously improves performance on tasks like Parameter Golf and NanoChat without human intervention by leveraging lineage feedback.
Thesis Labs launched Automode, a system that autonomously conducts ML research on Optiver’s trading dataset.