• Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    AI

    Question’s Gambit reportedly reaches 96.6% recall on BrowseComp-Plus

    The team says the search-agent module focuses on the first retrieval move, reporting about six times fewer agent search calls with the same BM25 index and agent loop.

    3 Sources, 20d ago, first seen 20d ago

    TLDR

    In its September 24, 2026 announcement, the team behind Question’s Gambit says the module ranked first on the BrowseComp-Plus leaderboard for recall, using BM25 as its only retriever. It reports 96.6% recall with about six times fewer agent search calls, crediting a better first retrieval move while keeping the index and agent loop unchanged.

    Combined views

    —

    3 Sources, first seen 20d ago

    — likes— comments— saves— reposts

    Combined views

    —

    3 Sources, first seen 20d ago

    — likes— comments— saves— reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    3 Sources

    Negar Arabzadeh @COLM@NegarEmpr1/ We’re excited to share Question’s Gambit module for search agents. ♛ 🥇Question Gambit got first on the BrowseComp-Plus leaderboard for recall with BM25 as our only retriever! 📈 It focuses on the first retrieval move in search agents and got 96.6% recall with about 6 times fewer agent search calls. Same BM25 index. Same agent loop. Just a better opening move. 📄 Paper: https://arxiv.org/abs/2609.1441220d
    Connor Shorten@CShorten30RT @NegarEmpr: 1/ We’re excited to share Question’s Gambit module for search agents. ♛ 🥇Question Gambit got first on the BrowseComp-Plus l…20d
    Andrew Drozdov@mrdrozdovRT @NegarEmpr: 1/ We’re excited to share Question’s Gambit module for search agents. ♛ 🥇Question Gambit got first on the BrowseComp-Plus l…19d
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    3 Sources

    Negar Arabzadeh @COLM@NegarEmpr1/ We’re excited to share Question’s Gambit module for search agents. ♛ 🥇Question Gambit got first on the BrowseComp-Plus leaderboard for recall with BM25 as our only retriever! 📈 It focuses on the first retrieval move in search agents and got 96.6% recall with about 6 times fewer agent search calls. Same BM25 index. Same agent loop. Just a better opening move. 📄 Paper: https://arxiv.org/abs/2609.1441220d
    Connor Shorten@CShorten30RT @NegarEmpr: 1/ We’re excited to share Question’s Gambit module for search agents. ♛ 🥇Question Gambit got first on the BrowseComp-Plus l…20d
    Andrew Drozdov@mrdrozdovRT @NegarEmpr: 1/ We’re excited to share Question’s Gambit module for search agents. ♛ 🥇Question Gambit got first on the BrowseComp-Plus l…19d
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet