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

    Two COLM 2026 papers explore collective agent evolution and more efficient model reasoning

    A researcher says their groupโ€™s papers are titled Group-Evolving Agents and Length Value Models.

    Xin Eric Wang @ COLM 2026XE
    2 Sources, 1h ago, first seen 1h ago

    TLDR

    A researcher attending COLM 2026 in San Francisco says their group has two papers this year. Group-Evolving Agents explores how agents can improve through collective evolution; Length Value Models explores how models can reason more efficiently.

    Combined views

    981

    2 Sources, first seen 1h ago

    Combined views

    981

    2 Sources, first seen 1h ago

    13 likes
    13 likes
    2 comments
    4 saves
    2 reposts
    2 comments
    4 saves
    2 reposts
    Featured Source

    Sentiment

    Positiveโ€”โ€”Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Sentiment

    Positiveโ€”โ€”Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    โ€”

    Not ranked yet

    Today's Rank

    โ€”

    Not ranked yet

    2 Sources

    Xin Eric Wang @ COLM 2026@xwang_lkIn SF for #COLM2026! Our group has two papers this year, exploring two directions Iโ€™m especially excited about: ๐Ÿงฌ Group-Evolving Agents โ€” how agents can improve via collective evolution. ๐Ÿ“ Length Value Models โ€” how models can reason more efficiently. Say hi if youโ€™re around!1h

    2 Sources

    Xin Eric Wang @ COLM 2026@xwang_lkIn SF for #COLM2026! Our group has two papers this year, exploring two directions Iโ€™m especially excited about: ๐Ÿงฌ Group-Evolving Agents โ€” how agents can improve via collective evolution. ๐Ÿ“ Length Value Models โ€” how models can reason more efficiently. Say hi if youโ€™re around!1h