Skip to content
Nov 20Fri
  1. arXiv Board & Classic Game AI56

    Paper proposes conditional safety theorem and a posteriori certificate for subgame solving in multiplayer games

    The paper proposes a conditional safety theorem for subgame solving in multiplayer games with three or more players acting independently, decomposes the best-response gap upper bound of the post-solve strategy into four terms, and gives an a posteriori certificate that can check any submitted update.

    Why it matters: The certificate requires only one best-response computation per opponent, making it usable for online safety verification of real-time multiplayer solvers.

Nov 18Wed
  1. arXiv Game World Models & Generation58

    InertialWorld: A video world model with inertia as a prior

    Researchers propose InertialWorld, which treats inertia as a structural prior for autoregressive video prediction, letting existing scene evidence carry over time instead of being rebuilt at every step. Its core Inertial Memory maintains both a dense Eulerian grid and persistent Lagrangian carriers, transports carrier content according to action-conditioned motion, and then fuses old and new content with a learned gate. In experiments on robotic manipulation, 3D game simulation, and open-world navigation, the model's autoregressive prediction performs comparably to strong video world model baselines, and the code is open-sourced on GitHub.

    Why it matters: The paper treats inertia as a structural prior for autoregressive video world models, letting readers see how its memory mechanism reduces error accumulation in long-sequence prediction.

Nov 6Fri
  1. Grok Bot Research58

    HairDeck open-sources a model that generates stylized hair with UVs, colors and spring bones from a single image

    Researchers from Tsinghua University, CMU and The Chinese University of Hong Kong open-sourced HairDeck, which generates stylized hair cards with per-card UVs and colors from a single character image, along with the spring bone chains that drive them. The model is split into weights including Image DiT, Card VAE, Color DiT and Chain DiT, outputs GLB hair meshes, and can be attached to the provided VRoid Studio template character to export VRM 0.x avatars.

    Why it matters: The original post releases the weights of each module and a local running workflow, which readers can use to judge whether single-image hair asset generation can fit into their own character pipelines.

Oct 25Sun
  1. arXiv Game AI33

    WMEval: Evaluating interactive world models grounded on physical simulations

    WMEval evaluates interactive world models against Unity physics simulation as a reference. The benchmark covers 9 scenes and assesses action controllability, scene and character consistency, prompt following, kinematics, fluid dynamics, physical causality, and lighting. By executing matched action sequences in the simulator and in the world models and comparing the results, the paper argues that existing models still have substantial room for improvement in dimensions that standard perceptual metrics fail to capture.

  2. arXiv Game AI50

    WMEval: Evaluating interactive world models grounded on physical simulations

    WMEval evaluates interactive world models against Unity physics simulation as a reference. The benchmark covers 9 scenes and assesses action controllability, scene and character consistency, prompt following, kinematics, fluid dynamics, physical causality, and lighting. By executing matched action sequences in the simulator and in the world models and comparing the results, the paper argues that existing models still have substantial room for improvement in dimensions that standard perceptual metrics fail to capture.

    Why it matters: Existing world model evaluations mostly look at perceptual similarity of frames; this work instead uses Unity physics simulation as a reference, adding a check of physical causal consistency.

Oct 21Wed
  1. arXiv Game AI46

    Fig: automated multiagent behavior elicitor

    Fig is an agent system that intervenes in game environments in a targeted way to elicit six types of target behavior: cooperation, exploitation, deception, tacit coordination, betrayal, and sabotage. The paper reports that across valid scenarios generated by Fig, models attempted the target behavior in an average of 45.2% of rounds. For game-and-behavior combinations with a control, interventions raised the attempt rate by an average of 10.9% over matched control games. The authors argue that multiagent environments can serve as a programmable, controllable, and reproducible testbed for behavior evaluation, and the code is publicly available on GitHub.

    Why it matters: It turns evaluation of multi-agent social behavior from passive observation into programmable environment intervention, useful for researchers who want to design reproducible test environments.

  2. arXiv Game AI31

    Fig: automated multiagent behavior elicitor

    Fig is an agent system that intervenes in game environments in a targeted way to elicit six types of target behavior: cooperation, exploitation, deception, tacit coordination, betrayal, and sabotage. The paper reports that across valid scenarios generated by Fig, models attempted the target behavior in an average of 45.2% of rounds. For game-and-behavior combinations with a control, interventions raised the attempt rate by an average of 10.9% over matched control games. The authors argue that multiagent environments can serve as a programmable, controllable, and reproducible testbed for behavior evaluation, and the code is publicly available on GitHub.

Oct 10Sat
  1. arXiv Game AI49

    MC-EvoBench: Auditing experience-driven self-improvement in Minecraft agents with 19 evolution chains

    The paper builds a controlled Minecraft benchmark, MC-EvoBench, which audits experience-driven self-improvement in agents using 19 registered evolution chains (12 main evaluation chains and 7 calibration or probe chains). It requires the target world to be reset and allows only declared agent artifacts to cross the source-target boundary.

    Why it matters: The paper uses paired probes to separate capability changes from leftover resources and uneven source exposure, making it a useful reference design for controlled evaluation of self-improving agents.