HarnessEval-W: Agentifying the Evaluation of Visual Worlds
2026-08-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a new way to evaluate world models that does more than just give a single score. Their system, called HarnessEval-W, breaks down each test into smaller parts and uses different agents to check each one carefully, similar to how humans think through a problem. This method produces a clear explanation for the final result, making it easier to understand why the model was judged a certain way. They tested it on many models and cases, finding that its judgments matched human opinions well and offered detailed feedback.
world modelsbenchmarkingevaluation metricsagent-based evaluationhierarchical reasoningcausalityphysics simulationtransparent reasoningdiagnostic toolsopen source benchmark
Authors
Weiliang Chen, Haowen Sun, Jun Gao, Jiawei Chi, Hanyang Wang, Qiyu Dai, Yihao Li, Hao Li, Jingnan Gao, Yi-Hsin Hung, Xingzhuo Guo, Shangchen Miao, Zhiyuan Shi, Xiang Li, Fengrui Tian, Weihua Du, Ziqi Huang, Shenyuan Gao, Siqiao Huang, Mingyu Liu, Yifei Li, Shizun Wang, Xi Wang, Tianqi Zhang, Xue Luo, Xiyin Ren, Jinshan Ren, Xiaoyang Shen, Xiaobo Hu, Zhiyang Dou, Mingyu Ding, Yichao Yan, Xinchao Wang, Yizhou Wang, Shilong Liu, Wenzhao Zheng, Yueqi Duan, Yuan Gong, Ziwei Liu, Ming-Yu Liu, Jialong Wu, Jiangran Lyu, Fangfu Liu
Abstract
A benchmark should deliver more than a scalar score: what makes an evaluation trustworthy is the reasoning that justifies the score. This is especially critical for world models, where judging a rollout requires understanding whether physics, causality, and world state evolve correctly. Humans spot such violations naturally, yet no existing benchmark automates this capability: metrics are computed brute-force, leaving no reasoning chain that can be examined or verified. We introduce HarnessEval-W, an agentified evaluation pipeline that brings the harness paradigm from the LLM ecosystem to world model benchmarking. Rather than applying a fixed rubric, HarnessEval-W interprets the context of each evaluation case, decomposes the evaluation question into measurable subproblems, and spawns specialized sub-agents, each equipped with tailored context and diagnostic tools to reason over its own subproblem. The parent agent then validates the gathered evidence and summarizes it into the final verdict. This hierarchical workflow turns every evaluation into a transparent evidence tree whose complete reasoning chain justifies the result. We apply HarnessEval-W to 18 representative world models over 330 evaluation cases. Its judgments closely align with human preferences while providing verifiable, fine-grained diagnoses of every generated rollout. We open-source the full pipeline as a live benchmark and invite the broad community to contribute to grow new skills and evaluation cases as world models evolve.