Rule based agent wins bargaining games without real time language model calls
Beating the Pool, Not the Game: A White-Box Equilibrium Agent for Language-Based Economic Games
Robotics
Summary
The paper presents sudsho, an agent that plays negotiation and persuasion games without using online language models during moves. It sets its goals based on how well previous players performed, while making sure its offers and acceptances stay within safe limits using equilibrium rules. The agent's decisions depend only on what it can see in the game, making its behavior easy to verify. Tested over many games, sudsho performed well while requiring no costly language model calls in real time.
What this means in practice
- •For game developers: Implement negotiation agents in games that do not need expensive language model calls during play but still make strategic offers based on past player data.
- •For customer support automation teams: Create scripted negotiation bots that efficiently set and adjust offers using equilibrium bounds to improve customer bargaining interactions without real-time AI inference.
Authors
Sudhanshu Srivastava, Faisal Aqlan
Abstract
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.