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

AI game bots can reportedly top human leaderboards using match replays, but mostly stall on complex-rule games

A post describing a Tsinghua paper says replays beat win/loss-only feedback in all three games tested.

1 Source, 1h ago, first seen 1h ago

TLDR

A post describing a Tsinghua paper says AAArena uses 12 games and 1,920 archived human programs as rivals. Its coding agent studies replays and rewrites its bot without changing model weights. Detailed replays beat win/loss-only feedback in all three games tested: the Pacman bot reached rank 1 with replays versus rank 11 without. Tripling the match budget did not take any of four stuck bots to rank 1.

Combined views

—

1 Source, first seen 1h ago

— likes— comments— saves— reposts

Combined views

—

1 Source, first seen 1h 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.

1 Source

Rohan Paul@rohanpaul_aiNew Tsinghua paper finds that AI agents improving game bots from match replays can top human leaderboards, but mostly stall on games with complex rules. Getting AI to learn a winning game strategy from a limited number of matches is still hard, especially against changing rivals. They built AAArena from 12 games in Tsinghua's yearly bot-building contest, with 1,920 archived human programs as rivals. A coding agent, with its model weights unchanged, reads the rules, picks opponents, studies replays, and rewrites its bot within a match budget. Detailed replays beat win/loss-only feedback in all 3 games tested. With replays, a Pacman bot reached rank 1, versus rank 11 without them. Tripling the match budget did not push any of 4 stuck bots to rank 1. – arxiv. org/abs/2610.12341 Title: "Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition"1h
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    1 Source

    Rohan Paul@rohanpaul_aiNew Tsinghua paper finds that AI agents improving game bots from match replays can top human leaderboards, but mostly stall on games with complex rules. Getting AI to learn a winning game strategy from a limited number of matches is still hard, especially against changing rivals. They built AAArena from 12 games in Tsinghua's yearly bot-building contest, with 1,920 archived human programs as rivals. A coding agent, with its model weights unchanged, reads the rules, picks opponents, studies replays, and rewrites its bot within a match budget. Detailed replays beat win/loss-only feedback in all 3 games tested. With replays, a Pacman bot reached rank 1, versus rank 11 without them. Tripling the match budget did not push any of 4 stuck bots to rank 1. – arxiv. org/abs/2610.12341 Title: "Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition"1h
    Today's Rank

    #16

    Today's Rank

    #16