arXiv Machine Learning November 2, 2026 By Vartan Shadarevian, Kia Ghods, Alex Kenich, Anany Kotawala

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

Read the original on arXiv Machine Learning →

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.

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 Machine Learning.

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 AI

Aug 18

The Fragility of Strategic Thinking in Large Language Models

arXiv:2510. 10813v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly applied to domains that require reasoning about other agents' behavior, such as negotiation, policy design, and market simulation.

By Enric Junque de Fortuny, Veronica Roberta Cappelli

llms agents

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

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

arXiv AI

Oct 12

SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire

SpireBench evaluates long‑horizon strategic play by having large language models play the full commercial deck‑builder Slay the Spire, a game where early choices determine long‑term success. Across 20 LLMs at the highest difficulty, frontier models beat heuristic baselines and match average human performance but lag far behind experts, especially as runs lengthen. The benchmark reveals that strong models excel in early fights but misjudge risk over a run, and that their performance depends partly on prior game knowledge rather than on memories written during play.

By Scott C. Lowe, Sander W. Keemink

llms agents benchmarks

arXiv AI

Sep 28

Game Arena: Strategic LLM Evaluation in Competitive Environments

Game Arena is an open, continuously expanding platform that evaluates large language models through competitive games, allowing head‑to‑head matchups in structured environments. Unlike static benchmarks, it prevents performance saturation by increasing gameplay difficulty as models improve. The report outlines the infrastructure and presents three pilot games—Chess, Poker, and Werewolf—covering perfect information, imperfect information, and multiplayer settings, and details evaluation metrics and competition results.

By Bovard Doerschuk-Tiberi, Yao Yan, Justin Chiu, Hann Wang, Timothy Chung, Martyna Plomecka, John Schultz, Jon Lipovetz, Clayton Drazner, Yuchen Zhuang, Jaimie Hwang, Nate Keating, Riley Jones, Andrew Lee, Oran Kelly, Ian Gemp, Michael Aaron, Laurel Prince, Kate Larson, Jeff Moser, Harrison Jobe, Chad Woodford, Siqi Liu, Andrew Wang, Bo Chang, Christopher D'Mello, Diane Chaleff, Addison Howard, Johnny Yip, Chuck Sugnet, Antonio Gulli, Meghan O'Connell, Will Cukierski, Nenad Tomasev, Dima Yeroshenko, Kinjal Parekh, Roxanne Daniel, Marc Lanctot, Domino Weir, Elsa Dong, Daniel Hennes, Melissa Nalubwama, Robert Fraser, Ryan Trostle, Jun Peng, Tom Mason, Lloyd Hightower, Chiamaka Chukwuka, Yuexiang Zhai, Phoebe Kirk, Yi Su, Yuting Han, Jie Ren, Chris Prichard, Sahand Sharifzadeh, Karim Hakimzadeh, DJ Sterling, Meg Risdal, Kate Olszewska, Ya Xu, Orhan Firat, Minmin Chen

llms benchmarks

One email a morning, machine-written

Related stories

Solver-Guided Reasoning for Mixed-Equilibrium Strategies

The Fragility of Strategic Thinking in Large Language Models

Choosing LLMs for Strategic Agent Interactions

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

SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire

Game Arena: Strategic LLM Evaluation in Competitive Environments