LATIDIA · Robótica

Vencer a la piscina, no al juego: un agente de equilibrio de caja blanca para juegos económicos basados en el lenguaje

arXiv: 2611.10932v1Tipo de anuncio: nuevo Resumen: Describimos sudsho, un agente basado en reglas para la competencia GLEE que juega a la negociación, la negociación y la persuasión con llamadas LLM de tiempo de inferencia cero. Los juegos se puntúan como p

La noticia

arXiv:2611.10932v1 Announce Type: new 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),