Dream-RSI: Turning Past Searches into Tests of Search Strategy
Recorded attempts let policies test different continuations without repeating discovery. The Lasso results show why fewer search calls and faster solver execution must be read separately.
AnalysisExpand summaryCollapse summary
Dream-RSI replays completed discovery trees to evaluate and rewrite exploration-policy code under fixed models and evaluators. A small tree shows how two policies reach different observations from the same starting information. The Gemini-3.1-Pro Lasso comparison reports 317 discovery calls versus 550 and lower mean solver runtime, but the paper attributes that mean improvement to RCV1 while the other five held-out datasets become slower. Incumbent retention protects the mean replay score only on the identical fixed history pool.