DiscoveryRSI-27B

Headlines · 1

1. 9h
   PhAI Labs releases DiscoveryRSI research agent and 27B model

   PhAI Labs, working with several universities and research institutions, proposed DiscoveryRSI and trained DiscoveryRSI-27B using a hypothesis-credit attribution mechanism, releasing the paper, code and models. The system stores evolving hypotheses and test plans in a research hypothesis tree and is paired with DFM-Bench, which evaluates hypothesis revisions, research paths and whole research episodes. The team reports that DiscoveryRSI's group scored 6.3% in a literature cross-check, the highest of five model groups, while the Claude Opus 5 group scored 2.3% and ranked last; it cautions that group sample sizes differ and the comparison is descriptive, so it does not prove the hypotheses were adopted or validated by later research.

   机器之心 · 🔥 9

Experience and discussion from the community

Share my DiscoveryRSI-27B experienceAsk about DiscoveryRSI-27B