Skip to content

Fields

Game agents latest news

AI that acts in games: generalist game agents, LLM-driven bots, agents in Minecraft, StarCraft and other environments, benchmarks and open frameworks.

111 picks55 in the last 30 days170 collected in all

Updated

Picks archive · Page 6

Oct 7Wed101–111
  1. arXiv Game AI34

    Recursive Game Creator: an agentic harness for experience-oriented game development

    Recursive Game Creator proposes an agentic framework for experience-oriented game development. Four components (Designer, Builder, Player and Reviewer) form a recursive development loop that aims to push rough prototypes toward more engaging games.

    Why it matters: The paper brings player experience into a recursive game-generation loop, in contrast to generation methods that only check whether a program runs. It suits readers interested in evaluation for game generation.

Oct 6Tue
  1. arXiv Game AI42

    SpeedrunBench launches to benchmark frontier LLM agents' strategy formation with speedruns across 9 games

    The paper introduces SPEEDRUNBENCH, a speedrunning benchmark that evaluates frontier LLM agents on 9 different games. Agents must repeatedly refine their strategies over long-horizon actions, review their own performance and use the knowledge they have gained to be faster than their past selves and others. Experiments show frontier agents approach human world records on simple platformers, but on longer, more complex games they still lag behind human performance under practical budget constraints; the authors see the benchmark as a long-term testbed for studying agents' strategy formation ability.

    Why it matters: The paper uses speedrun tasks across 9 games to probe agents' strategy formation, showing near-human world-record performance on simple platformers while still trailing on long, complex games.

  2. arXiv Game World Models & Generation71

    Ten-hero MOBA continuous Dyna loop study reaches 70.2% radiant-side win rate in real matches

    The paper trains a structured multi-agent world model for a full ten-hero MOBA and plugs it into a continuous asynchronous Dyna loop; policies learn only from 1,400-tick imagined matches and win 70.2% of real matches as radiant (421 wins in 600 games, 95% CI 66.4-73.7), win none as dire, and also lose every game against the built-in opponent in self-play.

    Why it matters: The paper evaluates the world model in real matches; the Dyna loop raises the radiant-side win rate from 33.7% to 70.2%, and the model and evaluation protocol are open-sourced.

  3. arXiv Game AI41

    Attacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied Agents

    The researchers propose Attacca, which trains a vision goal-conditioned policy on complete search-to-interaction trajectories so long-horizon embodied agents can carry on to the next task from the position, orientation and world state left by the previous one. The method uses context-decoupled goal sampling, pairing each demonstration with a class-compatible masked goal image from another world, and provides supervision beyond action imitation through a goal mask prediction head, while introducing behavior phase conditioning that distinguishes the Search, Approach and Interact phases.

    Why it matters: The paper brings state-continuous long-horizon execution into the evaluation and reports success rate and completion comparisons against the strongest baseline.

  4. arXiv Game AI51

    PlaySuite: a large-scale benchmark for interactive visual intelligence covering more than 5K open-source games

    The authors propose PlaySuite, a large-scale benchmark for evaluating interactive visual intelligence built on more than 5K open-source games from PyWeek and itch.io, spanning engines including Pygame, HTML5, Godot and Unity.

    Why it matters: The benchmark covers open-source games across multiple engines and provides a unified evaluation protocol, useful for comparing how different models sustain action in dynamic visual environments.

  5. Unity67

    Unity demos prototyping a UI Toolkit main menu from concept art with the CLI and an AI agent

    Unity has released a tutorial video showing how an AI agent, working through the Unity CLI and starting from concept art and a short brief, can build a usable main menu interface directly inside the Unity editor.

    Why it matters: The original walks through the full agent workflow from concept art to a runnable main menu, and its approach of command-line testing with screenshot feedback can be carried over to your own projects.

Oct 4Sun
  1. arXiv Game AI39

    Code2Games: enabling coding agents to generate playable game worlds from natural language

    Wei Wu proposes Code2Games, an agent framework that lets coding agents build structured game worlds on top of a Blender world generated from the same game intent. The framework coordinates scene analysis, gameplay planning, constrained game world generation and engine customization through shared scene and gameplay representations, and when adapting to Unreal Engine 5 uses compilation diagnostics, runtime feedback and playtest results for execution-guided refactoring.

    Why it matters: The paper coordinates the generation stages with shared scene and gameplay representations and compares generation quality on a benchmark containing ten fixed game prompts, making it easy to measure against existing approaches.

Oct 1Thu
  1. arXiv Game World Models & Generation54

    Paper proposes auditable world model framework Kepler, achieving 100.00 RHAE on public ARC-AGI-3 games

    The paper proposes Kepler, an open-source framework that represents hypotheses as executable world models and verifies them through backtracking transition checks and conditional prediction checks.

    Why it matters: The authors release Kepler's verification pipeline and cost records, which can be used to compare the verifiable performance of different agents on ARC-AGI-3.

Sep 15Tue
  1. AI and Games62

    Breaking down the AI design in the Command & Conquer and Red Alert source code

    AI and Games examined how the AI in Command & Conquer and Red Alert is implemented, drawing on the source code EA released alongside Command & Conquer Remastered Collection and made available on GitHub.

    Why it matters: Using the remastered edition source code EA made public, the article breaks down unit tasks, commander states and pathfinding in the two early RTS games.

Jul 5Sun
  1. AI and Games38

    Forza Motorsport's New Drivatar Is Lying to Players

    Forza Motorsport's AI was rebuilt from the ground up, and the Drivatar system no longer relies on human play data. In a video, AI and Games argues that what the rebuilt Drivatar shows players is not how it actually works.

    Why it matters: The video explains why Forza Motorsport's ground-up rebuilt Drivatar no longer depends on human play data, and points out the gap between its behavior and what players see.

Jun 30Tue
  1. AI and Games49

    Why Bowie Knife99 Is a Bug in Forza's Drivatar System

    In its 85th video, AI and Games explains why Drivatar "Bowie Knife99" in Forza Horizon 6 became both a community meme and a public enemy in online races, tying the phenomenon to Turn 10's changes to AI driver behavior in 2023's Forza Motorsport.

    Why it matters: It traces the link between Bowie Knife99's rise to fame and Turn 10's changes to driver AI behavior in 2023's Forza Motorsport, offering a comparison with the older Drivatar system.