arXiv AI October 21, 2026 By Phurinat Polasa, Thanapon Thanadunpremdet, Phatthanasak Kraiduang, Saksorn Ruangtanusak

Teaching AI Agent to Play Poker Strategically Through Preference Optimization

The paper investigates whether compact AI agents can display strategic behavior in poker under hidden information and whether preference optimization can surpass static and zero‑shot policies. After evaluating a static baseline and three frozen language models (SmallThinker, Qwen3, Gemma‑3), the authors introduce Strategic Preference Optimization with KL‑anchored Equilibrium (SPOKE), which blends teacher‑relative value penalties, policy anchoring, risk constraints, and structured rationale supervision. SPOKE outperforms other methods on Kuhn and Leduc games, achieving the lowest mean exploitability and the highest six‑max top‑1 agreement while maintaining teacher‑consistent behavior.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Aug 12

Multiplayer Nash Preference Optimization

arXiv:2509. 23102v4 Announce Type: replace Abstract: Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models with human preferences.

By Fang Wu, Xu Huang, Weihao Xuan, Zhiwei Zhang, Yijia Xiao, Guancheng Wan, Xiaomin Li, Bing Hu, Peng Xia, Jure Leskovec, Yejin Choi

llms reinforcement-learning benchmarks safety

arXiv AI

Oct 15

Choosing LLMs for Strategic Agent Interactions

arXiv:2610.18354v1 Announce Type: new Abstract: Game-theoretic benchmarks claim that large language model (LLM) strategic decision-making varies across game types, interaction structures, and capabil...

By Arastun Mammadli, Herbert Woisetschl\"ager, Jawad Fayaz, Shiqiang Wang

llms rag agents reinforcement-learning benchmarks safety

arXiv AI

Sep 10

The Internal Anatomy of Strategic Choice in Large Language Models

arXiv:2609.07478v1 Announce Type: new Abstract: Large language models act as strategic agents and models of human choice, yet choosing like a strategic agent does not mean computing like one. We reco...

By Vin\'icius Ferraz, Leon Houf, Enrico Ferrea

llms agents

arXiv Machine Learning

Aug 10

Solver-Guided Reasoning for Mixed-Equilibrium Strategies

arXiv:2608. 06741v1 Announce Type: new Abstract: Reasoning in large language models (LLMs) is often grounded in human text, human demonstrations, and human-generated rationales.

By Han Wang, Philippe Beardsell, Boning Li, Aaron Sasmita, Shuai Li, Hongyuan Zha, Baoxiang Wang

llms benchmarks

arXiv Machine Learning

Sep 4

LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games

The paper explores a runtime strategy-selection framework where a large language model (LLM) guides a pre‑trained reinforcement learning (RL) policy for non‑player characters (NPCs) in a Unity combat game without altering the underlying policy. Five NPC agents sharing a PPO policy were compared in a baseline setup and an LLM‑augmented setup, where a locally hosted Mistral 7B model assigns one of four tactical tags every five seconds based on live game state. Across 600 episodes against three scripted opponents, the LLM‑augmented agents more than doubled their win rate against a Balanced opponent, improved performance against an Evasive opponent, but struggled against an Aggressive opponent due to over‑reliance on encirclement; analysis of 2,430 strategy selections revealed limited zero‑shot differentiation with the model favoring Surround in 83.8% of cases.

By Hrithika Deepu Nair, Kayvan Karim

llms agents reinforcement-learning

arXiv AI

Oct 15

GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games

arXiv:2610.13995v1 Announce Type: cross Abstract: Post-training large language models (LLMs) on two-player zero-sum games provides a verifiable reward, and the gains have been shown to transfer to ge...

By Weixian Waylon Li, Jiaxin Zhang, Han Zhou, Chengzu Li, Ke Wang, Fengxiang He, Yiwen Guo

llms reinforcement-learning efficiency benchmarks

One email a morning, machine-written

Related stories

Multiplayer Nash Preference Optimization

Choosing LLMs for Strategic Agent Interactions

The Internal Anatomy of Strategic Choice in Large Language Models

Solver-Guided Reasoning for Mixed-Equilibrium Strategies

LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games

GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games