Reproduce “Collaborative Search Meets Large Language Models: An Empirical Study” 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
Peiyuan Gong, Jiamian Li, Erhan Zhang, Fengming Liang, Kexin Liu, Yue Chen, Jiaxin Mao
The authors compare Google Search, in-chat search tools, and LLM agents for pairs conducting collaborative web research. CoSearchAgent interprets Slack conversation, searches the web, and returns cited answers, while SearchAgent presents result lists. Pairs using CoSearchAgent clicked fewer results than with SearchAgent, but interactions lasted longer than with Google Search, and reports were less rich than SearchAgent reports.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.