Reproduce “AI Agent Swarms as Researchers: Progress, Challenges, and Open Questions” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sergey Gusev, David E. Bernal Neira
The authors describe a swarm of coding agents given a research scope, literature, tools, and permission to continue working, while choosing problems and reviewing results. Within weeks, it produced 45 potential papers across five theoretical areas and eight proposed catalysis programs. Review is estimated at over seven months of full-time work, but correctness and novelty remain unestablished for the unreviewed corpus.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.