Game-Playing Agents

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, up 75% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 119

Jul 31, 2026cs.AI

MirrorCraft: Paired Evaluation under Hidden Rule Changes in Minecraft

With the prosperity of the large language models (LLMs), it has become an interesting topic: how do LLM-based agents work in Minecraft? Unfortunately, most existing benchmarks evaluate them under fixed game mechanics. High performance in these settings does not show whether an agent can continue making progress when familiar recipes, drops, and other rules change. In this paper, we introduce MirrorCraft, a paired benchmark for evaluating agents under hidden rule changes in Minecraft. Each Mirror world is a copy of its paired Vanilla world, with selected server-side rules modified by the corresponding datapack. Terrain, spawn, resource placement, objective, interface, and action budget remain matched within every Vanilla-Mirror pair. MirrorCraft includes five controlled biomes, six rule suites, three progression objectives, two model families, and six agent configurations under a shared Mineflayer interface. We evaluate task progress with deterministic advancement milestones and success rate and use the Rule Intervention Effect (RIE) to measure the performance change between matched Vanilla and Mirror worlds. The experiments show that hidden rule changes have strongly different effects across suites. Among the configurations evaluated without rule descriptions, ReAct achieves the highest pooled Mirror score. Providing the exact rules yields modest gains in average progress and completion across all three objectives. MirrorCraft extends Minecraft evaluation beyond fixed mechanics and provides a controlled setting for studying how agents use gameplay outcomes when the rules of the current world differ from familiar ones.

Jianxin Gao, Beini Hu, Runze Li +6

China Agricultural University, Beijing, China · Beijing Normal University, Beijing, China · Jilin University, Changchun, China +2

Game-Playing Agents LLM Agent Evaluation AI Agent Benchmarks Agentic AI

Jul 30, 2026cs.AI

Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3

ARC-AGI-3 turns abstraction into an interactive problem of skill acquisition. A player must infer an unfamiliar game's rules, hidden state, and goal while maintaining action efficiency because every move counts. We formalize these environments as parameterized rendered deterministic Moore machines and introduce Tycho, a coding-agent system that constructs and uses game-specific models during interaction. Tycho separates actionable observations from intermediate animation, level-completion, and game-over frames. From this structured history, an agent can model, test, plan with, repair, or bypass a free-form executable hypothesis. In one matched public-set run per policy, we compare four orchestration policies on all 25 public games using Claude Opus 4.8 under matched inference budgets. Actor-requested delegation to a model builder obtains the highest observed mean Relative Human Action Efficiency (RHAE), 88.49. With this selected policy, GPT-5.6 Sol and Opus 5 both reach 100.00 RHAE and complete all 183 levels. Their game-balanced first-run human-replay midranks are 98.5 and 100.0. Opus 5 uses 61% fewer scored actions than the aggregate official human baselines. Automatic repair after verification failures produces models that reproduce observed transitions much more accurately, yet reaches only 83.07 RHAE. Transition match indicates whether a simulator reproduces observed dynamics, not whether it has identified the objective or improves the next action. Strong play also requires deciding when to construct, repair, use, or bypass a model. We call this joint problem active abstraction: generating a testable model from costly interaction and deciding when acquiring or using it is worth its cost.

Jens Lehmann, Andrei Aioanei, Sahar Vahdati

Dresden University of Technology · Amazon · TIB – Leibniz Information Centre for Science and Technology +1

Game-Playing Agents AI Coding Agents World Models State Abstraction ARC-AGI AI Agent Benchmarks

Jul 29, 2026cs.AI

Belief-Guided Decision Making with Uncertainty Gating in the Game of Go

Recent advancements in Computer Go, driven by AlphaZero and MuZero, rely heavily on Monte Carlo Tree Search (MCTS) to correct the errors of the neural network policy. While effective on massive computational clusters, this dependence creates a critical bottleneck on consumer-grade hardware, where the computational cost of tree management severely limits inference rates. Furthermore, without deep search, these models suffer from hallucination, proposing moves with high confidence that are strategically fatal. This paper introduces a novel Belief-Guided architecture that disentangles the Policy head from a distinct Belief head. Unlike traditional value functions, the Belief head acts as an internal simulator and independent critic, modeling epistemic uncertainty and strategic stability. By integrating memory mechanisms (Transformer/GRU) to handle long-term dependencies and the Ko rule, and utilizing a gating mechanism to filter overconfident policy errors, our model shifts the burden of intelligence from runtime search to parametric "intuition." Experimental results demonstrate that this approach significantly improves search-free win rates and reduces hallucination, enabling professional-level play on limited hardware where massive MCTS is infeasible.

Mehrad Yaghoubi, Azam Bastanfard, Abbas Jalilvand +1

Department of Computer Engineering, Ka.C, Islamic Azad University, Karaj, Iran

Game-Playing Agents Decision-Making under Uncertainty Epistemic Uncertainty

Jul 29, 2026cs.AI

CaM-Wolf: Causal-Aware Multimodal Agents for Social Deduction Games

Social deduction games (SDGs) such as Werewolf have become challenging testbeds for AI agents. These games require complex social skills such as reasoning, deception, and collaboration. While recent advances in large language models (LLMs) have driven significant progress in SDG agents, current approaches are predominantly text-based, overlooking the multimodal nature that is fundamental to human social interaction. To bridge this gap, we introduce CaM-Wolf, the first SDG agent that integrates multimodal perception and generation. CaM-Wolf processes video inputs from other players, employs a causal-aware Reasoner trained via reinforcement learning to establish logical chains between observable behaviors and hidden roles, and presents itself through an animated avatar. Our experiments and user study show that CaM-Wolf achieves superior agent gameplay performance and enhances the quality of human-AI interaction. This work represents a significant advancement towards creating more human-like AI agents capable of participating in nuanced social dynamics. Our code is available at https://3dagentworld.github.io/avatar_wolf.

Zheng Zhang, Nanjie Yao, Jiarui He +3

The Hong Kong University of Science and Technology (Guangzhou) · Nanyang Technological University · Shanghai Jiao Tong University

Game-Playing Agents Social Deduction Games LLM Agents Multimodal Agents

Jul 28, 2026cs.CL

CAST: Game Solvers as Turn-Level Teachers for LLM Agents

Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR) relies on sparse final rewards that reveal little about which decisions determine success. Denser process signals could supply this missing turn-level credit, but existing sources are hard to keep both cheap and accurate. We observe that changes in a game solver's state value reveal whether an action advances the state toward success. Building on this insight, we propose CAST (Credit Assignment from Solver Teachers), which converts these value changes into solver advantages and injects them into RLVR as turn-level signals. We further show that, under a soft-optimal solver assumption, maximizing the solver advantage is equivalent to on-policy distillation from the solver, requiring only scalar values rather than teacher logits. Across Sokoban, Minesweeper, and Rush Hour, CAST outperforms all trained baselines on every game under both in-domain and unseen-difficulty evaluation and achieves the highest average zero-shot performance on ALFWorld and WebShop. Our code is available at https://github.com/Wloner0809/CAST.

Yu Wang, Yi-Kai Zhang, Wentao Shi +8

University of Science and Technology of China · 4Meituan, China · 2Nanjing University +1

Reinforcement Learning Game-Playing Agents Credit Assignment in RL Step-Level Credit Assignment in RL Reinforcement Learning with Verifiable Rewards RL for LLM Agents

Jul 22, 2026cs.CV

Cortex: Compact Behavior Cloning for Quake with Frozen Visual Features

We study how far a deliberately simple behavioral-cloning policy can progress in a visually rich first-person game before adding reinforcement learning or explicit memory. Cortex is a compact Quake policy with 10.98 million trainable parameters in a six-layer transformer over a frozen DINOv3 encoder. It is trained on the Quake subset of the public Pixels2Play corpus: 6,849 recordings (about 474.7 hours), represented as 17.09 million cached decision frames with keyboard and mouse actions. One sampled training epoch uses 517,048 four-frame windows and takes 3.3 minutes of policy-head optimization on one RTX 5080, excluding one-time feature extraction. We evaluate two independent batches of 20 stochastic, 120-second episodes on Quake E1M1. Cortex does not complete the level, but every episode reaches the opening door, button room, and gate descent; 19 of 20 episodes in each batch record at least one kill. Under the same time-controlled harness, released P2P-150M and NitroGen checkpoints remain shallower in five matched-duration episodes each. These comparisons are limited by small reference samples and different native interfaces. Ablations show that denser visual tokens improve combat and survival, while longer optimization and naive action history improve offline metrics without consistently improving play. The remaining failures are consistent with covariate shift and motivate targeted corrective data. We release the policy implementation, checkpoint, and a representative rollout.

Dzmitry Malyshau

Game-Playing Agents Visuomotor Policy Learning Imitation Learning Behavior Cloning

Jul 22, 2026cs.AI

Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning

LLM-based game agents often perform poorly on more complex tasks. This work examines whether these failures are linked to limited spatial reasoning and evaluates whether causal prompt augmentation and multi-step planning can improve win-rates while managing response latency. Using the open-source Qwen3 model family, we conduct experiments across varying model scales, reasoning modes, and planning horizons. We further introduce a focused GVGAI benchmark consisting of three custom games with five difficulty levels to isolate spatial navigation. The evaluation follows two paradigms: an initial ``positioning experiment'' to test an agent's ability to find its exact coordinates, and a study of game-play success. 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. Win rates decrease as game levels and layout complexity increase, validating the benchmark's difficulty scaling. Integrating causal context into the prompts tends to improve the agents' success rates, particularly for bigger models. While enabling thinking mode and longer planning horizons significantly improve performance, multi-step planning further reduces mean per-step response times, offering a practical trade-off between reasoning depth and execution speed.

Mohit Jiwatode, Ronja Fuchs, Robin Schmöcker +2

Institute for Information Processing · SDU Metaverse Lab

Game-Playing Agents LLM Agent Evaluation AI Agent Benchmarks Spatial Reasoning LLM Agent Planning

Jul 16, 2026cs.AI

Concept-Guided Spatial Regularization for World Models in Atari Pong

World models are usually evaluated as components of model-based reinforcement learning (MBRL) systems, while the world models themselves are rarely studied in isolation. We examine five representative visual world-model agents in Atari Pong: DreamerV3, DIAMOND, TWISTER, Simulus, and STORM. After reproducing their training pipelines and matching the reported agent performance, we freeze the learned world models and evaluate them with a closed-loop rollout diagnostic: a policy trained separately from the corresponding MBRL agent interacts with each frozen model, and the generated video trajectories are inspected for visual and dynamical errors. Across all five models, the rollouts contain clear failures, including ball disappearance, incorrect ball motion, and invalid ball-paddle interactions. Beyond visual trajectories, we further evaluate them with pixel-space zero-shot MBRL, where a new policy is trained entirely inside a frozen world model and then evaluated in the real environment. Across all five models, the resulting policies substantially underperform those produced by the corresponding original MBRL training pipelines. The gap is particularly large for DreamerV3, whose mean return drops from -5.5 to -20.9, near the minimum Pong return of -21. We hypothesize that insufficient modeling of task-critical concepts, such as the ball in Pong, may contribute to these failures. We therefore propose Concept-Guided Spatial Regularization (CGSReg), an auxiliary pixel reconstruction loss applied to segmented concept regions. Experiments show that CGSReg improves both closed-loop rollouts and pixel-space zero-shot MBRL in DreamerV3, DIAMOND, and TWISTER. Its effects vary across the remaining models and evaluation metrics, indicating that CGSReg alone does not address all world-model bottlenecks.

Yukuan Lu, Zaishuo Xia, Weyl Lu +1

UC Davis

Game-Playing Agents World Model Learning World Model Evaluation Model-Based RL

Jul 15, 2026cs.MA

Equilibrium stability as a driver of cooperation among Q-learners

Algorithmic collusion among pricing algorithms has raised concerns about sustained supra-competitive prices and their implications for social welfare. Existing work has largely focused on the probability that reinforcement-learning algorithms converge to cooperative strategies, typically under the assumption that exploration vanishes over time. Motivated by the observation that algorithms deployed in practice are likely to continue exploring in order to remain adaptive to changing environments, we study learning dynamics under constant exploration. In this setting, the relevant question is no longer whether an algorithm converges to a particular strategy profile, but rather what fraction of time the algorithms spend playing cooperative strategies. Even in the benchmark case of the repeated Prisoner's Dilemma with one-period memory, this yields high-dimensional stochastic learning dynamics, for which a complete analytic treatment is intractable. We show that cooperative strategies can be dominant in this time-averaged sense and derive a boundary predicting when such dominance arises, based on the expected dynamics of the Q-learning process. Extensive simulations show that this boundary is a strong predictor for non-defection-dominated behaviour under epsilon-greedy Q-learning.

Janusz M. Meylahn, Maximilian Schäfer

University of Twente, Department of Applied Mathematics, Drienerloolaan 5, 7522 NB Enschede, The Netherlands. · Institut Mines-Télécom Business School, Department of Data Analytics, Economics, and Finance. 9 Rue Charles Fourier, 91000 Evry, France.

Game-Playing Agents Repeated Games Q-Learning Algorithmic Collusion Cooperative MARL

Jul 14, 2026cs.AI

Dynamic Resource Allocation for Ensemble Determinization MCTS

Simulation-based algorithms are especially suited for high-uncertainty environments such as adversarial board games with significant elements of randomness and hidden information. In particular, several Monte Carlo Tree Search (MCTS) variants are commonly used in such domains. In this paper, we propose a series of enhancements for Ensemble Determinization MCTS, introducing two axes for dynamic resource allocation. First, Dynamic Number of Determinizations, increases or decreases the number of currently used determinization trees depending on the behavior of so-far search. Second, Dynamic Simulation Allocation, splits the simulation budget nonuniformly across the determinization trees, using simulation-to-simulation decisions to choose the tree with potentially the best knowledge gain. As benchmark domains, we used three popular tabletop games: Jaipur, Lost Cities, and Splendor. Testing our proposed enhancements in iteration- and time-based settings showed that particular configurations yield a statistically significant increase in the algorithm's strength.

Jakub Kowalski, Adam Ciężkowski, Artur Krzyżyński +1

Faculty of Mathematics and Computer Science, University of Wrocław · Department of Advanced Computing Sciences, Maastricht University

Game-Playing Agents Imperfect-Information Games Monte Carlo Tree Search

Jul 14, 2026cs.CV

WanToFight: Real-Time Generative Game Engine for Multi-Player Combat Interaction

We present WanToFight, a generative game engine that simulates real-time, two-player The King of Fighters '97 (KOF~'97) gameplay from keyboard input. Prior generative game engines target either single-player first-person settings or non-real-time cooperative scenarios; multi-player control, real-time inference, complex physical interaction, and adversarial gameplay have not been jointly addressed. WanToFight closes this gap with three components built on the Wan-1.3B video diffusion transformer: a streaming autoregressive generator with block-causal attention and a rolling KV cache; a visually grounded Player Association module that binds each player's keyboard signal to a character identity; and a gated, locally causal keyboard injection module trained with a single-player-to-full-gameplay curriculum. A four-step DMD-distilled student paired with a pruned VAE decoder sustains 30FPS at 512x384 on a single NVIDIA RTX 5090 over the duration of a complete match. To our knowledge, WanToFight is the first generative game engine to combine multi-player control, real-time inference, complex physical interaction, and adversarial gameplay in one system.

Li Hu, Guangyuan Wang, Peng Zhang +1

Tongyi Lab, Alibaba

Action-Conditioned Video Generation Video Diffusion Models Game-Playing Agents Autoregressive Video Generation Controllable Video Generation

Jul 9, 2026cs.LG

AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision

AlphaZero has demonstrated that a neural-guided Monte Carlo Tree Search can achieve superhuman performance, but strong play does not necessarily imply perfect play. We study this gap in two oracle-evaluable domains with contrasting structure: Connect Four, a solved partisan game with exact game-theoretic values, and Chomp, an impartial game whose optimal play is governed by Grundy-number structure. Under a unified self-play

+

MCTS pipeline, we compare vanilla AlphaZero, a multi-frame variant (limited to Chomp), and an AlphaZero Auxiliary Loss (AZAL) that adds oracle-derived policy supervision. We find that vanilla AlphaZero achieves strong play across both domains but cannot preserve the exact trajectories required for optimal play: in Connect Four, it fails to maintain the optimal line of play, while in Chomp, it fails to consistently restore the

g=0

invariant. On rectangular Chomp boards, multi-frame inputs alone do not remove this gap. Nevertheless, AZAL substantially improves oracle consistency across multi-seeded full-game traces and sampled-state evaluations. On Chomp, AZAL reaches perfect full-game oracle consistency on 10x11 and high but not complete consistency on 9x10; on Connect Four, AZAL improves oracle-match rate and delays the first oracle mistake, but does not reach perfect play.

Brent Kong, Tejas Ram, Tony Yue Yu

Department of Mathematics · California Institute of Technology · Department of Computer Science

Game-Playing Agents Self-Play RL Game Theory Monte Carlo Tree Search Sparse-Reward RL

Jul 9, 2026cs.LG

Open-ended Multi-agent Autocurricula via Visual Inspection of Policies with Multi-modal LLMs

Open-ended curricula in Reinforcement Learning (RL) aim to train generally-capable agents by identifying tasks that facilitate learning increasingly complex skills. A major challenge when designing such curricula is assessing task difficulty relative to the agent's current learning progress. While previous work has explored using scalar task scores or textual summaries of the agent's behavior, here we study a different approach: directly inspecting policy behavior via recorded episode videos. We introduce a simple yet effective instantiation of this approach which leverages a Video Language Model (VLM) to both process these videos and provide curriculum recommendations, which we call Visual Inspection of Policies (VIP). Since videos can naturally contain any number of controllable agents, we empirically study VIP on the StarCraft Multi-Agent Challenge (SMAC). We show that even with a lightweight and openly accessible VLM (VideoLLaMa2-7B), VIP can use policy videos to generate more effective curricula than both its text-only ablation and methods that rely on scalar task scores.

Lorenzo Pantè, Andrea Fanti, Roberto Capobianco

Sapienza University of Rome, Italy · Sony AI, Zurich, Switzerland

Game-Playing Agents Curriculum RL LLM-Guided RL Curriculum Learning Multi-Agent Reinforcement Learning

Jul 8, 2026cs.LG

Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26

Testing is a major effort for the gaming industry, requiring a significant part of development budget and people power. We present a case study on a development version of the ice hockey game EA SPORTS NHL 26, for which human playtesters test the goalie AI for behavioral exploits. To reduce the effort of re-testing the goalie AI after every game or behavior modification in the development phase, we propose Reward-Adaptive Iterative Discovery (RAID), a novel approach to automatically find exploits using an iterative Reinforcement Learning (RL) approach that trains a population of goal scoring agents. While previous approaches can already successfully find exploits, RL algorithms tend to overfit to a single solution. We introduce a simple extension on top of existing RL algorithms, such that they find multiple diverse high-quality solutions. For our first deployment of this approach, within a single experiment we were able to find six hockey scoring exploit strategies that were qualitatively similar to those that playtesters had found in hours-long manual testing sessions.

Florian Fuchs, Jessy Gosselin-Grant, Boris Skuin +5

Electronic Arts (EA)

Automated Software Testing Reinforcement Learning Game-Playing Agents AI Agent Evaluation

Jul 7, 2026cs.LG

A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong

Reinforcement learning agents for imperfect-information card games are only as strong as the opponents they train against, and they are hard to grade, since they beat a random opponent over 99 percent of the time and only tie copies of themselves. So we build a strong, fixed, rule-based expert for Gin Rummy and use it only as a yardstick, never for training. It beats every agent we trained 70 to 99 percent of the time. Across more than a hundred runs, we isolate what makes a lightweight agent stronger. Trust region updates, a well-aimed reward, a curriculum of tougher opponents, warm starting, and keeping the best checkpoint all help, and stacking them lifts a self-play champion from about 30 to 36 percent against the expert. Several ideas did not pay off. Short-term and longer-term reward shaping, learned state embeddings, imitation and DAgger, and a live large language model opponent were each unhelpful, too slow, or too heavy to train at scale. Comparing MLP, convolutional, set-based, attention, and recurrent encoders shows that extra capacity does little to break the ceiling, suggesting the limit is information rather than network size. We add standard baselines (neural fictitious self-play and information set Monte Carlo search) and confirm the approach carries over to Leduc Hold'em, where the optimum is computable. The result is a lightweight, game-agnostic recipe that trains competitive agents without training on the expert, for any game a small model can handle, reported with robust statistics and released as a reusable package.

Nima Kelidari, Mohammadsaeed Haghi, Mahdi Salmani

University of Southern California

Reinforcement Learning Game-Playing Agents Self-Play RL Imperfect-Information Games AI Agent Evaluation Reward Design for RL

Jul 7, 2026cs.AI

FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games

We present FootsiesGym, an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information game. Built on HiFight's minimalist 2D fighting game Footsies, it isolates the cyclic, non-transitive strategic interactions of fighting game neutral play while remaining simple enough for efficient analysis. We provide a vectorized simulator that enables high-throughput training on standard hardware, making the environment accessible and reproducible. We describe the design of the environment, benchmark several reinforcement learning algorithms, and discuss open research directions it enables. The code is available at https://github.com/como-research/FootsiesGym.

Chase McDonald, Nathan Tsang, Wesley N. Kerr

Como Research · Riot Games

RL Benchmarks Game-Playing Agents Imperfect-Information Games Zero-Sum Games Agent Benchmarks

Jul 6, 2026cs.CY

When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games

As large language models are deployed as autonomous agents that communicate intentions before acting, a critical safety question is whether agents that publicly commit to actions will honor those commitments. We place LLM agents in repeated

n

-player games with a three-stage protocol that separates private intent, public announcement, and final action, allowing us to identify whether each deviation from a stated announcement was already planned during private deliberation. Evaluating three frontier models across six games in homogeneous and heterogeneous groups over 10 rounds, we report two findings. First, when agents deviate from their announcements, the deviation is predominantly already stated in their private plan (exceeding 90% in the highest-deception conditions), yet this is not a fixed model property: the same model ranges from perfect honesty to near-total deviation across games. Second, different models interpret announcements incompatibly, some as binding commitments and others as cheap talk, producing payoff gaps that emerge in Round~0 and persist across all 10 rounds. Systems that combine models from different providers therefore cannot assume shared announcement semantics and require empirical testing of model interactions before deployment.

Jerick Shi, Terry Jingcheng Zhang, Bernhard Schölkopf +2

Carnegie Mellon University, Pittsburgh, USA · Jinesis AI Lab, Vector Institute and University of Toronto, Toronto, Canada · EuroSafeAI +1

Multi-Agent LLM Systems Game-Playing Agents Deception in Language Models Repeated Games LLM Agent Evaluation LLM Agent Reliability

Jul 2, 2026cs.MA

Congestion-Based Slot Pricing in a Railway Auction Game

We present a multi-agent system for studying the allocation of discrete, congested resources among heterogeneous strategic agents, motivated by the problem of railway slot allocation under deregulation. Multiple operator-agents, differing in size and capacity, interact through a shared auction mechanism over repeated rounds under time-constrained decision-making. The mechanism combines a congestion-based base price that increases with aggregate demand with an asymmetric corrective adjustment that penalises the agent requesting the most slots and rewards the agent requesting the fewest, and is designed to mitigate strategic dominance by large agents while preserving transparency and congestion sensitivity. We formulate the interaction as a repeated game with incomplete information and implement the system as a real-time, web-based multi-agent environment in which human participants control individual agents and observe live marginal-cost and competitor feedback. We report exploratory observations from two structured sessions with domain experts acting as operator-agents. The congestion mechanism responds to aggregate demand as designed and the corrective incentives are actively triggered, but agents representing large operators persist with high-request strategies despite the penalty, suggesting that corrective pricing is necessary but not sufficient to neutralise strategic dominance in this multi-agent setting. A post-session debrief indicates that participants' decisions were driven by the assumed agent role rather than personal disposition, and provides qualitative support for strategic motives, such as preserving market presence and raising rivals' costs, operating alongside short-term profit maximisation. We discuss implications for multi-agent mechanism design under asymmetric budgets and outline directions for analytical validation and larger-scale multi-agent experiments.

Bill Roungas, Sebastiaan Meijer

Panteion University, Athens, Greece · Institute of Communication and Computer Systems, Athens, Greece · KTH Royal Institute of Technology, Stockholm, Sweden

Mechanism Design Game-Playing Agents Repeated Games Dynamic Pricing Online Resource Allocation

Jun 29, 2026cs.AI

SAT-RTS: A systematic framework for tactical knowledge extraction and visualization-based analysis in real-time strategy games

Efficient tactical knowledge extraction and analysis in real-time strategy (RTS) games micromanagement are constrained by the high-dimensional coupled state-action sequential data and the black-box decision-making process. Current research rarely provides a hierarchical visualization-based attribution analysis from the perspective of data decoupling and abstraction. To facilitate interpretable tactical knowledge extraction and visualization-based analysis in RTS games, a systematic framework named state-action-tactic analysis pipeline (SAT-RTS) is proposed. To decipher the deep-seated drivers of critical decisions in RTS learning systems, this work integrates interpretable visualization with the automated extraction of latent tactical patterns from high-dimensional sequence data. By adapting a cluster-centric BK-tree algorithm and incorporating specialized distance metrics designed to quantify multi-aspect similarities, the proposed framework facilitates robust state-stream abstraction. Furthermore, a rule-based multi-label extraction method is developed to transform unstructured state-action sequences into discrete and interpretable tactical labels, effectively bridging the gap between raw behavioral data and high-level tactical insights. By holistically integrating these computational methods into a hierarchical visualization-based pipeline, the proposed framework effectively addresses the challenges of processing massive real-time data streams while providing fitness landscape visualizations and analytical insights to decipher deep-seated tactical drivers. Comprehensive experiments demonstrate that the proposed SAT-RTS significantly enhances the interpretability and efficiency of tactical analysis in complex RTS environments.

Chunhui Bai, Changhe Li, Yuqiang Li +2

School of Artificial Intelligence and Automation, China University of Geosciences, Wuhan 430074, China · Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems, Wuhan 430074, China · Engineering Research Center of Intelligent Technology for Geo-Exploration, Ministry of Education, Wuhan 430074, China +2

Game-Playing Agents Interpretability in RL

Jun 29, 2026cs.AI

SAGA: Scene-Aware, Goal-Evolving Agents for Long-Horizon Strategy Game Planning

Long-horizon strategic planning in complex strategy games requires coordinating tightly coupled decision domains, including technology, economy, diplomacy, and military, across hundreds of turns under imperfect information. Existing LLM-based agents face three challenges in this setting. They recover little relational structure, such as distance or threat, from raw coordinate observations. They serialize the entire growing game state into every prompt and plan all domains in a single output, so the context eventually overflows and urgent domains crowd out long-term ones. The only reward is a lagged final score, which provides no progress signal within or across games.<br/><br/>We present SAGA, an LLM multi-agent framework that addresses these challenges with three mechanisms: a Map-Semantic Scene Graph that renders typed entity relations as concise per-entity text, a Tool-Augmented Planner that retrieves state on demand and routes disjoint per-domain directives to specialist controllers, and a Dual-Horizon Feedback Loop that sets intermediate goals within a game and distills causal lessons across games. On CivRealm, a benchmark built on the strategy game FreeCiv, SAGA attains the highest mean final score among six methods, the statistically strongest gains on infrastructure, and a 27% reduction in output tokens. With cross-game evolution enabled, it reaches the highest score over five successive games.

Tianyu Jin, Shuo Chen, Yida Wang +6

Beijing University of Posts and Telecommunications · Beijing Institute for General Artificial Intelligence (BIGAI)

Multi-Agent LLM Systems Game-Playing Agents Long-Horizon LLM Agents LLM Agent Planning Self-Evolving Agents

Jun 26, 2026cs.AI

GPTNT: Benchmarking Real-Time Collaboration Between Multimodal Agents on Keep Talking And Nobody Explodes

Multimodal models are increasingly deployed to solve tasks collaboratively with humans or other artificial agents. Existing benchmarks show that these models possess many of the required component capabilities, but the conditions that coincide in collaboration, including time pressure, information asymmetry, and imperfect communication, are usually studied in isolation. We introduce GPTNT, a benchmark built on the cooperative video game Keep Talking and Nobody Explodes, in which two agents must coordinate to defuse procedurally generated bomb puzzles against a live countdown. One agent can see and manipulate the bomb but does not have the defusal instructions; the other has the instructions but cannot see or manipulate the bomb. Neither agent can succeed alone: success requires effective and efficient communication. Unlike turn-based proxies, GPTNT requires agents to act asynchronously and communicate in real time. GPTNT is designed to separate collaboration from reliance on memorized solutions: the instruction manual, the partner, or both can be withheld to isolate what a model derives in the moment from what it already knows. We show that GPTNT poses a substantial challenge for state-of-the-art systems: none of the closed- or open-source models we test defuses a single bomb in real time, a bar that human players clear. Through controlled experiments, we identify critical weaknesses in state tracking, efficient action under time pressure, ambiguity handling, and error recovery. We release GPTNT as a benchmark for collaborative performance that current evaluations leave unmeasured. Because it runs on the real game, GPTNT benefits from procedural generation and inherits a living modding community, allowing the benchmark to evolve as models improve rather than being solved once and retired.

Amit Parekh, Sabrina McCallum, Kareem Al-Hasan +3

Heriot-Watt University · University of Edinburgh

Game-Playing Agents Multi-Agent Collaboration AI Agent Benchmarks Multimodal Agents Multi-Agent Communication

Jun 26, 2026cs.CL

Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs

Theory-of-mind evaluations of large language models typically use dyadic social-deduction games, where every observable cue points to a single hidden side, so a model with strong language priors can score well without ever simulating opponents' incentives. We extend the Werewolf game with a Jester, a third faction whose utility on peer suspicion is inverted because it wins by being voted out, so optimal play requires reasoning across three opposing utility functions. Across 60 games on GPT-4.1, DeepSeek-V3.1, and Llama-3.3-70B with Jester self-learning on and off, the Jester wins 60-70% of games while Werewolves never exceed 20%, and GPT-4.1 wolves vote the Jester out on day 1 in 60-70% of games, a strictly self-defeating action. Self-learning helps DeepSeek and Llama but hurts GPT-4.1, with the cost landing on Villagers rather than Werewolves. Only DeepSeek learns the subtle strategy of looking suspicious without looking intentionally suspicious, and it gains the most from the loop. Triadic incentive structure exposes a layer of multi-agent reasoning that dyadic deduction games leave invisible.

Avni Mittal

Game-Playing Agents Social Deduction Games Theory of Mind AI Agent Benchmarks Multi-Agent Reasoning

Jun 23, 2026cs.AI

Matilda: Engine-Agnostic Search with Human Policy Guidance

Chess engines have evolved from search-based systems optimized solely for strength to neural policies capable of modeling human decisions across much of the rating spectrum. Maia-3, the strongest human-like move policy for chess, models the typical moves of a given rating but does not model high Elo strength well (2500+ Lichess Elo) nor has an extensible architecture for modeling individual play style. On the other hand, search-based engines like Stockfish are far stronger than any known human but struggle to model human-like play. To solve these problems, we present Matilda, a permutation-invariant set transformer that re-ranks the full legal-move distribution produced by a frozen Maia-3 and improves it along both dimensions with one 1.7M-parameter model. Matilda uses Maia-3 to provide both global context and search candidates. Context is encoded from Maia-3's hidden representation, time control, and an optional 32-dimensional player-style vector, while the top-16 candidate moves are optionally rescored by Stockfish. A zero-initialized head scatters per-candidate adjustments back into the policy logits, so the untrained model is exactly Maia-3 and every gain is value-added under full-vocabulary NLL. On a 2500+ Elo benchmark from Lichess, Matilda improves on Maia-3 by +0.5-0.6% below 2800 but +4.3%, +11.9%, and +21.9% at 2800-2900, 2900-3000, and 3000+, respectively, and an additional +0.41% overall from player-style embeddings. Ablations show that the improvements are primarily driven by the engine-derived features, the mechanism is not engine-specific, and the gains survive memorization, sibling, and account audits while preserving Maia-3 at 1000-2500 Elo. Because search supervision is modular, Matilda naturally supports interchangeable search engines, demonstrated by replacing Stockfish with an AlphaZero-family engine.

Jason Carlson

Game-Playing Agents Transformer Chess

Jun 23, 2026cs.AI

The Latent Bridge: A Continuous Slow-Fast Channel for Real-Time Game Agents

A real-time agent for general computer use - with games as the most demanding case - must act within tens of milliseconds while still planning over seconds. These two regimes sit at opposite ends of the latency-quality tradeoff. A reasoning VLM (Qwen3-VL-8B-Thinking) deliberates effectively but requires ~1.5 s per response - far too slow for a 15 Hz control loop. In contrast, a reactive VLM (MiniCPM-o 4.5) acts in milliseconds but underperforms on planning-heavy tasks. We couple two frozen models of matched scale (9B reactive, 8B reasoning), leaving the communication channel as the sole trainable component. The standard coupling is a Text Bridge (T): the slow model writes a suffix the fast model reads. We introduce a learned continuous Latent Bridge (L) that projects the slow model's residuals into the fast model's input-embedding space in a LLaVA-style manner, avoiding any text round-trip; both are compared against Fast-Only (F). On 7 Atari games and a driving domain (MetaDrive), tuning the action decoder per channel on held-out seeds, the Latent Bridge matches or beats the Text Bridge in every domain: it significantly improves two games (MsPacman +57%, RoadRunner +28%) and is a safe drop-in elsewhere. Combining both channels interferes destructively (RoadRunner -96%), so only one should be used. The benefit is highly predictable: the bridge helps if and only if slow reasoning already beats fast reaction (T > F) - the Latent and Text gains over Fast-Only move together at r=0.93. MetaDrive is the controlled negative, where the Latent Bridge is demonstrably inert because the Text Bridge adds no value. We release replay recordings and reproducible pipelines.

Bojie Li, Noah Shi

Pine AI · University of Washington

Game-Playing Agents VLM Reasoning Vision-Language Agents

Jun 22, 2026cs.LG

Superhuman AI for Generals.io Using Self-Play Reinforcement Learning

We present a superhuman AI agent for Generals.io, a real-time strategy game that requires both long-horizon planning and short-term tactics under strong imperfect information. Trained for four days on 4x NVIDIA H200 GPUs, our agent reaches #1 on the public 1v1 leaderboard of over 5,000 human players, leading the second-ranked player by the same margin that separates second place from 25th, and beats the two top-ranked humans head-to-head with a combined 199-70 record across 269 ladder matches. A key enabler is a JAX-native simulator that reaches tens of millions of frames per second on a single GPU, roughly a 10,000x speedup over the prior simulator. On top of this, we train a vision transformer policy end-to-end by self-play with a policy-gradient loop and sparse win/loss reward, using top-advantage sample filtering and an exponential moving average of the policy parameters. Taken together, our findings highlight what matters, and what does not, once a fast simulator removes the data bottleneck.

Matej Straka, Viliam Lisý, Martin Schmid

Department of Applied Mathematics, Charles University, Prague, Czech Republic · Department of Computer Science, Faculty of Electrical Engineering, Czech Technical University in Prague, Czech Republic · Charles University +1

Game-Playing Agents Self-Play RL Imperfect-Information Games

Jun 20, 2026cs.AI

IRumAI: Reinforcement Learning for Indian Rummy

Despite its massive player base and complex hidden-information dynamics, Indian Rummy has received no reinforcement learning attention. Existing agents rely on combinatorial search, which is tactically strong but slow at inference. We present IRumAI, the first RL agent for the domain. IRumAI integrates Proximal Policy Optimization (PPO), meld-aware observation encoding, deadwood-driven reward shaping, and a dual-branch convolutional architecture. IRumAI is RL-trained solely against weak heuristics, after a one-time behaviour-cloning warm-start on stronger demonstration data. It generalises to defeat the entire baseline hierarchy, including a 53.9% win rate against the strongest search-based opponent unseen during RL training. Bypassing explicit search, IRumAI requires just 0.33 ms per action, which is over 7,000x faster than the state-of-the-art heuristic. Ablations validate our architectural choices, and linear probing reveals that the network implicitly models the opponent's hidden hand from public interactions.

Vignesh Mohan

EURECOM Sophia Antipolis, France

Reinforcement Learning Game-Playing Agents Imperfect-Information Games

Jun 18, 2026cs.AI

Augmenting Game AI with Deep Reinforcement Learning

Immersion in video games depends not only on graphics, audio, and game mechanics, but also on the quality of in-game characters. Producing believable characters, or game AI, remains a significant challenge as behavioral complexity is hard to capture with hand-coded systems. Game AI is a source of immersion and engagement; however, the limitations stemming from the challenges of creating game AI often lead to frustration and the breaking of the illusion of realism within the game. The introduction of machine learning models opens the door to creating more believable, authentic, and relatable characters in games. The promise is that they either learn from interacting with the game, or from player data, to develop true human-like behavior. In this paper, we envision more applications of reinforcement learning for game AI in the future. For this to materialize, current research limitations are prohibitive to broad deployment across game genres. Therefore, we propose a framework for training reinforcement learning models with a set of requirements in mind that are suited towards game AI and game development. We present examples of games with reinforcement learning-augmented game AI and describe the practicalities of deploying player-facing machine learning agents in modern games. Furthermore, we identify bottlenecks and hard problems in these areas, which we believe offer promising research directions to accelerate the adoption of machine learning in game AI for the video game industry.

Alessandro Sestini, Joakim Bergdahl, Amir Baghi +3

Electronic Arts (EA), Stockholm, Sweden

Reinforcement Learning Game-Playing Agents

Jun 18, 2026cs.LG

Hierarchical Control in Multi-Agent Games: LLM-based Planning and RL Execution

Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to sparse rewards, large state-action spaces, and the difficulty of learning coordinated strategies. We propose a hierarchical architecture where a pretrained large language model (LLM) acts as a centralized strategic controller that selects among specialized RL skill policies for a team of agents, while RL policies handle reactive low-level execution. We evaluate this hybrid system in a competitive 2v2 King of the Hill environment against behavior tree (BT) and \emph{``Flat''} RL (end-to-end training without skill decomposition) baselines. The LLM+RL system achieves task performance statistically equivalent to hand-crafted BT (46.4% vs 51.5% win rate,

p=0.103

) while both significantly outperform Flat RL trained without skill decomposition. A user study (

n=15

) reveals that 60% of participants perceive LLM+RL agents as the most human-like (

p=0.027

), citing behavioral adaptability and tactical variability. These results demonstrate that pretrained LLM reasoning can effectively orchestrate pretrained RL skills, achieving competitive multi-agent coordination and superior perceived believability without manual rule engineering.

Jannik Hösch, Alessandro Sestini, Florian Fuchs +6

1Electronic Arts (EA) · 2KTH Royal Institute of Technology, Stockholm, Sweden

Sequential MARL Multi-Agent Coordination Game-Playing Agents Hierarchical RL LLM-Guided RL Multi-Agent Planning

Jun 17, 2026cs.AI

RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models

Modern Vision-Language Models (VLMs) often struggle with strategic reasoning, i.e., anticipating and influencing other agents' actions, under uncertainty in competitive and cooperative settings. Real-time strategy (RTS) games can be a natural testbed for diagnosing this limitation, as they demand coordination with allies, adaptation to opponents' strategy, and long-horizon planning under partial observability. However, existing RTS benchmarks offer limited evaluation scope, lack systematic competency diagnosis, and remain fixed in the pre-designed scenario coverage. To address these limitations, we present RTSGameBench, which is built on Beyond All Reason, a large-scale RTS game with an expanded battlefield that demands broader strategy diversity than the existing testbeds. The proposed benchmark provides evaluations through diverse gameplay across various matchup structures, diagnostic assessment via mini-games, each targeting an individual strategic competency, and extensible coverage via a self-evolving generation framework that converts free-form queries into new mini-games, improving over successive cycles. Additionally, for VLMs to operate in large-scale RTS games, we provide RTSGameAgent that manages units by an FSM with agentic memory. We empirically validate that multiple state-of-the-art VLMs do not perform well when matchups demand tighter coordination, multiagent coordination and when task scale increases.

San Kim, Daechul Ahn, Reokyoung Kim +3

Seoul National University

Multi-Agent Coordination Game-Playing Agents VLM Reasoning Agent Benchmarks

Jun 16, 2026cs.AI

WallZero: Mastering the Game of WallGo with Strategic Analysis

WallGo is a recently introduced strategic board game popularized by the 2025 Netflix series The Devil's Plan. Although played on a small 7 x 7 board, its combination of stone movement and wall placement yields high game-tree complexity and intricate strategic interactions. Despite its growing popularity, WallGo remains underexplored. This paper presents WallZero, an AlphaZero-based agent for the two-player WallGo setting. We introduce tailored action and feature designs to improve playing performance significantly. In the evaluation, WallZero defeats two professional Go players who participated in this study, securing on average 1.98x more territory per game. Beyond its strength, we use WallZero to assess game fairness and identify key strategies for mastering WallGo. Interestingly, our results show that the opening used in the Netflix series yields a more balanced game. Our code is available at https://rlg.iis.sinica.edu.tw/papers/wallzero.

Hsing-Yu Chen, Jérôme Arjonilla, I-Chen Wu +1

National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Academia Sinica, Taipei, Taiwan

Game-Playing Agents