arXiv AI
Jun 9
A Survey on Large Language Model-Based Game Agents
arXiv:2404. 02039v5 Announce Type: replace Abstract: Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity.
Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help
Related stories
arXiv AI
Jul 2
AI Native Games: A Survey and Roadmap
arXiv:2607. 00527v1 Announce Type: new Abstract: Generative AI now enables games to produce dialogue, quests, characters, images, and worlds at runtime.
arXiv AI
Oct 27
How Humans Learn Unfamiliar Worlds: A Think-Aloud Dataset on ARC-AGI-3
The paper presents the first dataset that captures how humans learn and use mechanisms in unfamiliar environments, using ARC‑AGI‑3 as a testbed. It includes 144 trajectories from 64 participants across 25 public games, each paired with time‑synchronized actions and think‑aloud audio, and 250 trajectories from large language model agents with and without harnesses. The dataset is annotated for mechanism triggers, action purposes, errors, and recovery, enabling a comparison of human and LLM cognition, highlighting differences in hypothesis testing, exploration, and use of qualitative representations.
arXiv AI
Sep 16
AI for Games in the Foundation Model Era
arXiv:2609.16679v1 Announce Type: new Abstract: Foundation models, alongside advances in learned game-world models, are reshaping AI across the game lifecycle. Beyond playing games, recent systems mo...
arXiv AI
Oct 7
SWE-Game: Can Coding Agents Build the Games We Want?
SWE-Game is a benchmark comprising 247 tasks based on 41 Godot games across 13 gameplay categories, testing coding agents on tasks such as brief-to-game, design-document implementation, skeleton completion, fault repair, and Godot-to-Unity porting. Evaluation uses engine-state checks, replay of certified reference inputs, and agent-authored demonstrations to judge mechanic correctness, playability, and post-repair behavior, supplemented by vision‑language rubrics for presentation. Across six models, Opus5 leads but overall scores stay below 60/100, highlighting common issues like omitted requirements and gameplay logic errors.
arXiv AI
Sep 17
Clueing up LLMs with Tool-Augmented Deductive Reasoning
The paper introduces a text-based, multi-agent version of the board game Clue to test multi-step deductive reasoning in large language models (LLMs). Six LLM-based agents (GPT‑4o‑mini and Gemini‑2.5‑Flash) play turn‑based games, and a tool‑augmented approach uses a structured possibility matrix to convert implicit game state into explicit remaining possibilities, thereby offloading memory and deductive constraints from the agents. The study compares this tool‑augmented method against a baseline to assess its impact on reasoning quality and task success in a strategic reasoning environment.
arXiv AI
Oct 7
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Learn2Play Bench is a new benchmark that tests how well large language model agents learn from experience in unfamiliar, text‑based games with novel or counterintuitive rules. The benchmark provides reproducible feedback, automatic scoring, and varied game instances to evaluate learning across repeated attempts and transfer to new situations. Findings show that retaining full action records aids learning, human players outperform agents, and the choice of harness significantly impacts performance and inference cost.
arXiv AI
Jul 1
From Multimodal Perception to Strategic Reasoning: A Survey on AI-Generated Game Commentary
arXiv:2506. 17294v3 Announce Type: replace-cross Abstract: The advent of artificial intelligence has propelled AI-Generated Game Commentary (AI-GGC) into a rapidly expanding research area, offering advantages such as scalable availability and personalized narration.
arXiv AI
Jul 7
Automating the Design of Embodied Agent Architectures
arXiv:2606. 30111v2 Announce Type: replace-cross Abstract: Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules.
arXiv AI
Jun 30
Automating the Design of Embodied AgentArchitectures
arXiv:2606. 30111v1 Announce Type: cross Abstract: Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules.
arXiv AI
Jun 9
ASH: Agents that Self-Hone via Embodied Learning
arXiv:2605. 14211v3 Announce Type: replace Abstract: Long-horizon embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales.
arXiv Computation and Language
Aug 28
MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft
MineExplorer is a benchmark designed to assess the open‑world exploration abilities of multimodal large language models (MLLMs) in Minecraft. It filters out tasks that rely heavily on Minecraft‑specific knowledge, organizes tasks into ReAct‑style capabilities, and composes atomic tasks into implicit multi‑hop challenges. A multi‑agent synthesis workflow creates reliable task graphs, sandbox scenes, and rule‑based milestone evaluators, and human evaluation confirms its superiority over a single‑agent baseline. Experiments show that while advanced MLLMs can handle many single‑hop tasks, they struggle with longer trajectories that require coordinating hidden prerequisites, and larger models or different thinking modes do not consistently improve performance.