跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.10932 · v1

Beating the Pool, Not the Game: A White-Box Equilibrium Agent for Language-Based Economic Games

首次提交 2026-11-08 03:44
版本更新 2026-11-08 03:44
雷达观测 2026-11-10 11:14
arXiv ↗PDF ↗

摘要

We describe sudsho, a rule-based agent for the GLEE Competition that plays bargaining, negotiation, and persuasion with zero inference-time LLM calls. Games are scored as payoff percentiles against an empirical pool of prior play on the same configuration, so pool percentiles set our demand targets while clamped equilibrium shares bound demands and acceptance. Every move is a deterministic function of the visible state (persuasion mixing aside), so alignment is verified by replaying the post-freeze move log through the policy. Across 117,280 games the agent reached an overall rating of 2056 at $0 inference cost, and the account, ranked by its best agent (a same-policy replica), placed 26th of 71 ranked accounts. A replay against three frozen snapshots of the opponent pool credits the pool-aware clamp with 274 to 330 points of mean per-game bargaining rating, an effect that holds where logged opponent decisions fix the replay.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-08 03:44 · 最新观测版本

Beating the Pool, Not the Game: A White-Box Equilibrium Agent for Language-Based Economic Games

We describe sudsho, a rule-based agent for the GLEE Competition that plays bargaining, negotiation, and persuasion with zero inference-time LLM calls. Games are scored as payoff percentiles against an empirical pool of prior play on the same configuration, so pool percentiles set our demand targets while clamped equilibrium shares bound demands and acceptance. Every move is a deterministic function of the visible state (persuasion mixing aside), so alignment is verified by replaying the post-freeze move log through the policy. Across 117,280 games the agent reached an overall rating of 2056 at $0 inference cost, and the account, ranked by its best agent (a same-policy replica), placed 26th of 71 ranked accounts. A replay against three frozen snapshots of the opponent pool credits the pool-aware clamp with 274 to 330 points of mean per-game bargaining rating, an effect that holds where logged opponent decisions fix the replay.

查看此版本解读 →查看此版本原文 ↗