paper-with-me

Papers

OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics

2026-06-08 · Mingxian Lin, Shengju Qian, Yuqi Liu, Yi-Hua Huang, Yiyu Wang, Wei Huang, Yitang Li, Fan Zhang, Zeyu Hu, Lingting Zhu, Xin Wang, Xiaojuan Qi arxiv

Vision-language model (VLM) agents are increasingly deployed in interactive game environments. Yet game benchmarks for VLM agents typically report a single first-attempt score per (agent, game) pair, focus on single-agent Solo play, and lack unified protocols for evaluating heterogeneous agent classes (commercial VLMs, open-weight VLMs, and specialized game policies) on the same footing. We address these gaps with OmniGameArena, a real-time benchmark of twelve newly built Unreal Engine 5 games spanning Solo (7), PvP (3), and Coop (2) with unified action interfaces, and the Improvement Dynamics Curve (IDC), an agentic-reflection harness in which a tool-using reflector LLM autonomously refines a bounded skill prompt across multiple rounds. Beyond cold-start leaderboard scores, IDC exposes two additional observables for each (agent, game) pair: how the score evolves across reflection rounds, and how the learned skill behaves on held-out task variants. We report these observables for twelve VLM agents on the cold-start leaderboard and four top agents under IDC.

📄 PDF Abstract BibTeX arXiv:2606.09826

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

NitroGen: An Open Foundation Model for Generalist Gaming Agents

2026-01-04 · Loïc Magne, Anas Awadalla, Guanzhi Wang, Yinzhen Xu 외 arxiv

We introduce NitroGen, a vision-action foundation model for generalist gaming agents that is trained on 40,000 hours of gameplay videos across more than 1,000 games. We incorporate three key ingredients: 1) an internet-s…

Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents

2025-10-27 · Zihao Wang, Xujing Li, Yining Ye, Junjie Fang 외 arxiv

We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned native keyboard-mouse inputs. Unlike API- or GUI-based approaches, this paradigm enables large-scale c…

AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research

2026-07-20 · Marjan Moodi, Xuankang Zhu, Fernando De Mesentier Silva, Harold Chaput 외 hf

World modeling is an unsettled field: architectures, training objectives, and state representations interact in complex ways, and no single recipe dominates across environments. This makes it an ideal testbed for AI codi…

WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games

2026-05-17 · Wenyu Zhang, Guoliang You, Tianlun, Haotian Zhao 외 arxiv

Coding agents are increasingly used as application builders, yet many evaluations still focus on source code, repository-level tests, or intermediate traces rather than the delivered application. We introduce WebGameBenc…

S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?

2026-08-31 · Jiajun Shi, Siyuan Tao, Yuhao Wu, Zexuan Wang 외 hf

Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience, yet existing agent benchmarks largely evaluate them as fixed policies. It therefore remains …