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

• URL: http://arxiv.org/abs/2605.23238v1
• Date: Fri, 22 May 2026 05:13:45 GMT
• Title: GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models
• Abstract summary: Large language models (LLMs) are increasingly deployed as economic agents in marketplaces, auctions, and bidding settings.<n>Existing strategic-reasoning benchmarks evaluate models on fixed canonical games.<n>We introduce GENSTRAT, which uses procedurally generated strategic environments to address these challenges.
• Score: 0.269220799495636
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly deployed as economic agents in marketplaces, auctions, and bidding settings. Anticipating their behavior in any specific deployment is hard. Existing strategic-reasoning benchmarks evaluate models on fixed canonical games. These benchmarks may saturate as the frontier improves, and they do not allow evaluators to generalize with confidence from benchmark performance to the varied and messy strategic environments that actual deployments involve. We introduce GENSTRAT, which uses procedurally generated strategic environments to address these challenges. Concretely, we generate a distribution of two-player zero-sum imperfect-information card games. The generator can draw fresh games on demand, allowing for evergreen evaluation and resistance to contamination. We pair the game distribution with a capability-profile methodology that decomposes model competence across six axes (state space, temporal depth, information sensitivity, opponent modeling, risk, and brittleness). We also introduce a jaggedness measure of within-distribution smoothness that detects when a model's advantage jumps unpredictably between strategically similar games. We sample 50 benchmark games from a 2,000-game generated pool and evaluate nine frontier and open-weight LLMs in a head-to-head tournament with over 36,000 matches. Newer frontier-tier models score higher on average. Beyond that average, models with near-identical overall strength show qualitatively different capability profiles, and two of the top three leaderboard models (gpt-5 and claude) are noticeably more locally volatile than the third (gemini-3.1-pro), despite being close in overall strength. Together, the capability profile and the jaggedness measure give a deployment-relevant diagnostic that the overall ranking alone cannot provide.

Related papers

• Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning [56.67877550139192]
  We conduct experiments across varying model scales, reasoning modes, and planning horizons.<n>We introduce a focused GVGAI benchmark consisting of three custom games with five difficulty levels to isolate spatial navigation.<n>Our results show that while larger models with an enabled thinking mode identify their positions more accurately, overall performance in coordinate matching remains limited for smaller models.
  arXiv  Detail & Related papers  (2026-07-22T12:10:45Z)
• Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games [69.57330692969543]
  We introduce RNG-Bench, a benchmark suite designed to isolate a base model's ability to reconstruct past observations.<n>RNG-Bench includes two complementary games: Matching Pairs, where card identities briefly revealed at specific locations must later be recalled, and 3D Maze, where egocentric views must be integrated into a spatial map.<n>The hardest configurations require contexts of roughly 128K tokens and 350 image inputs per episode, and remain far from saturated by frontier MLLMs.
  arXiv  Detail & Related papers  (2026-06-17T17:59:34Z)
• MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs [54.81359054218573]
  We introduce Mindgames, a multi-game arena and evaluation platform for large language models (LLMs)<n>Mindgames provides a unified interaction interface, TrueSkill-based rating, and full trajectory logging across four game environments.<n>We analyze 29,571 multi-agent games with turn-level observations, actions, and rewards, together with MG-Ref, a deterministic offline tournament protocol.
  arXiv  Detail & Related papers  (2026-05-28T07:33:47Z)
• Agent Island: A Saturation- and Contamination-Resistant Benchmark from Multiagent Games [0.0]
  We introduce Agent Island, a multiplayer simulation environment in which language-model agents compete in a game of interagent cooperation, conflict, and persuasion.<n>We rank players with a Bayesian Plackett-Luce model, allowing us to quantify uncertainty in player skill.<n>In 999 games involving 49 unique models, openai/gpt-5.5 dominates its peers with a posterior mean skill of 5.64, compared with 3.10 for the second-ranked model, openai/gpt-5.2, and 2.86 for the third-ranked model, openai/gpt-5.3-codex.
  arXiv  Detail & Related papers  (2026-05-05T21:24:58Z)
• AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents [75.67445299298949]
  AgentCPM-Explore is a compact 4B agent model with high knowledge density and strong exploration capability.<n>We introduce a holistic training framework featuring parameter-space model fusion, reward signal denoising, and contextual information refinement.<n>AgentCPM-Explore achieves state-of-the-art (SOTA) performance among 4B-class models, matches or surpasses 8B-class SOTA models on four benchmarks, and even outperforms larger-scale models such as Claude-4.5-Sonnet or DeepSeek-v3.2 in five benchmarks.
  arXiv  Detail & Related papers  (2026-02-06T08:24:59Z)
• BotzoneBench: Scalable LLM Evaluation via Graded AI Anchors [9.224594551677374]
  Large Language Models (LLMs) are increasingly deployed in interactive environments requiring strategic decision-making.<n>Recent game-based evaluations employ LLM-vs-LLM tournaments that produce relative rankings dependent on transient model pools.<n>Here we show that anchoring LLM evaluation to fixed hierarchies of skill-calibrated game Artificial Intelligence (AI) enables linear-time absolute skill measurement.
  arXiv  Detail & Related papers  (2026-01-22T13:15:08Z)
• Scheming Ability in LLM-to-LLM Strategic Interactions [4.873362301533824]
  Large language model (LLM) agents are deployed autonomously in diverse contexts.<n>We investigate the ability and propensity of frontier LLM agents through two game-theoretic frameworks.<n>Tests four models (GPT-4o, Gemini-2.5-pro, Claude-3.7-Sonnet, and Llama-3.3-70b)
  arXiv  Detail & Related papers  (2025-10-11T04:42:29Z)
• Model as a Game: On Numerical and Spatial Consistency for Generative Games [117.36098212829766]
  We revisit the paradigm of generative games to explore what truly constitutes a Model as a Game (MaaG) with a well-developed mechanism.<n>Based on the DiT architecture, we design two specialized modules: (1) a numerical module that integrates a LogicNet to determine event triggers, with calculations processed externally as conditions for image generation; and (2) a spatial module that maintains a map of explored areas, retrieving location-specific information during generation and linking new observations to ensure continuity.
  arXiv  Detail & Related papers  (2025-03-27T05:46:15Z)
• GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents [4.209869303518743]
  We introduce GameBench, a cross-domain benchmark for evaluating strategic reasoning abilities of large language models. Our evaluations use GPT-3 and GPT-4 in their base form along with two scaffolding frameworks designed to enhance strategic reasoning ability: Chain-of-Thought (CoT) prompting and Reasoning Via Planning (RAP) Our results show that none of the tested models match human performance, and at worst GPT-4 performs worse than random action.
  arXiv  Detail & Related papers  (2024-06-07T00:28:43Z)
• How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments [83.78240828340681]
  GAMA($gamma$)-Bench is a new framework for evaluating Large Language Models' Gaming Ability in Multi-Agent environments.<n>$gamma$-Bench includes eight classical game theory scenarios and a dynamic scoring scheme specially designed to assess LLMs' performance.<n>Our results indicate GPT-3.5 demonstrates strong robustness but limited generalizability, which can be enhanced using methods like Chain-of-Thought.
  arXiv  Detail & Related papers  (2024-03-18T14:04:47Z)
• Finding mixed-strategy equilibria of continuous-action games without gradients using randomized policy networks [83.28949556413717]
  We study the problem of computing an approximate Nash equilibrium of continuous-action game without access to gradients. We model players' strategies using artificial neural networks. This paper is the first to solve general continuous-action games with unrestricted mixed strategies and without any gradient information.
  arXiv  Detail & Related papers  (2022-11-29T05:16:41Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.