arXiv AI

Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions

The paper investigates why large language models (LLMs) struggle in strategic decision-making under incomplete information. It identifies two key gaps: an observation‑belief gap where LLMs’ internal representations of game states are accurate but brittle, and a belief‑action gap where converting these internal beliefs into actions is weak, leading to suboptimal payoffs. Experiments with Llama 3.1, Qwen3, and gpt‑oss confirm that acting optimally on decoded beliefs would improve outcomes in most games, highlighting a bottleneck in belief‑to‑action conversion.

arXiv AI
Aug 26

Confident at the moment of action: belief miscalibration in LLM play under hidden information

The paper investigates whether large language models (LLMs) correctly gauge their confidence when acting in a hidden‑information chess variant. In experiments where the location of a hidden royal piece is repeatedly relocated, the models’ stated probabilities about the piece’s position were almost never accurate at high confidence levels, with a calibration deficit concentrated in those high‑confidence events. Across multiple model configurations and providers, the same pattern emerged, and conventional evaluation metrics such as legality, cost, latency, and completion rate were found to be uncorrelated with belief quality, yet a model could still win the game despite poor confidence estimates.

By Bhushan Kashinath Joshi
arXiv Computation and Language
Oct 28

Game-Theoretic Solvers with Bayesian Opponent Modeling and Moral Rhetoric Framing for GLEE

The paper presents an agent designed for the GLEE Competition that engages in bargaining, negotiation, and persuasion games against human and AI opponents. The agent combines a classical game‑theoretic solver, an online Bayesian layer for estimating opponent archetypes, and a language model for generating messages. Experiments include 13,200 Monte Carlo games against 11 synthetic archetypes, an ablation study of the opponent‑modeling layer, and an analysis of 9,337 live‑game messages showing a strong correlation between moral rhetoric framing and buyer purchase decisions.

By Hayden Arnold
arXiv AI
Aug 25

Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games

The study examines how Theory of Mind (ToM) reasoning and prosocial beliefs influence large language models (LLMs) in the ultimatum game. By initializing LLM agents with Greedy, Fair, or Selfless beliefs and applying chain‑of‑thought or varying levels of ToM reasoning, the authors ran 2,700 simulations across several models, including o3‑mini and DeepSeek‑R1 Distilled Qwen 32B. Results show that ToM‑enhanced LLMs align more closely with human decision patterns, exhibit greater consistency, and achieve better negotiation outcomes, with Llama 3.3 70B producing the most belief‑consistent reasoning. whyItMatters":"The findings clarify the importance of incorporating Theory of Mind into LLMs to improve their alignment with human norms in cooperative decision‑making tasks."

By Neemesh Yadav, Yihuai Lan, Shan Dong, Mai Hieu Hien, Palakorn Achananuparp, Jing Jiang, Ee-Peng Lim
arXiv Machine Learning
Nov 2

GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models

GENSTRAT is a system that evaluates strategic reasoning in large language models (LLMs) by procedurally generating two-player zero-sum imperfect-information betting games on demand. Each game is scored across five complexity axes—state space, temporal contingency, opponent dependence, private information, and precision—and assessed via Monte Carlo simulation. Using this generator, the authors created a 50-game benchmark, ran a tournament of twelve frontier and open-weight models with over 40,000 LLM vs. LLM matches, and found that the performance gap on the hardest games is 1.7 times larger than across all games, with higher thinking budgets, opponent strategy disclosure, and tailored reasoning improving outcomes.

By Vartan Shadarevian, Kia Ghods, Alex Kenich, Anany Kotawala
arXiv AI
Sep 17

Recursive Reasoning or Statistical Extrapolation? In-Context Learning in Multi-Agent Interdependent Decision-Making

The paper investigates whether in-context learning (ICL) in large language model agents reflects genuine recursive reasoning or simply statistical extrapolation. By testing LLM agents in a public goods game with manipulated historical feedback, the authors compare decision quality to a rational expectations equilibrium benchmark. They find that disrupting historical patterns eliminates the benefits of longer context, especially in highly interdependent settings, indicating that ICL behavior aligns more with statistical extrapolation than strategic reasoning.

By Yu Liu, Wenwen Li, Yifan Dou, Guangnan Ye