WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity
- URL: http://arxiv.org/abs/2608.02603v1
- Date: Mon, 03 Aug 2026 17:59:54 GMT
- Title: WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity
- Abstract summary: We introduce WorldExam, a diagnostic benchmark spanning four levels: Visual Quality, Control Adherence, Spatial Consistency, and World Reactivity.<n>It comprises 1,474 cases across eight dedicated tasks and supports unified evaluation of camera-, action-, and language-driven model paradigms.<n> Evaluation of 20 representative models reveals a clear capability split. Camera-driven models excel at camera control, but their interfaces do not support dynamic interaction.
- Score: 75.96851880065331
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Controllable video generation models are increasingly being developed as world models. Accordingly, evaluating them in this role extends beyond the apparent appearance of generated videos to the inherent reactivity of the worlds they depict: the ability to infer from the scene state how the world should react and to generate plausible consequences not explicitly described in the input. Yet existing benchmarks mainly assess visual quality or explicit instruction fulfillment by checking whether requested actions and interaction outcomes are realized, leaving inherent reactivity underexamined. We introduce WorldExam, a hierarchical diagnostic benchmark spanning four levels: Visual Quality, Control Adherence, Spatial Consistency, and World Reactivity. It comprises 1,474 cases across eight dedicated tasks and supports unified evaluation of camera-, action-, and language-driven model paradigms. The World Reactivity level evaluates scene-conditioned reactions and goal-directed behaviors beyond what is explicitly specified in the input. Evaluation of 20 representative models reveals a clear capability split. Camera-driven models excel at camera control, but their interfaces do not support dynamic interaction; action-driven models control subjects more precisely but often leave the world unresponsive; and language-driven models perform better on interaction but follow complex controls less faithfully. No model combines broad task coverage with consistently strong performance, showing that high visual quality and explicit instruction fulfillment do not guarantee inherent reactivity.
Related papers
- WorldReward: Reward Modeling for Camera-Conditioned World Models [56.14617966299295]
We present WorldReward, a VLM-based pairwise preference reward model for camera-conditioned world models.<n>WorldReward decomposes paired videos into action-aligned chunks, organizes each chunk into structured visual evidence, and aggregates chunk-level decisions by voting into separate video-level action and visual-quality preferences.<n>WorldReward achieves the highest agreement on all three dimensions, exceeding GPT-5.5 by 3.42, 1.45, and 3.56 percentage points, respectively.
arXiv Detail & Related papers (2026-09-03T14:53:53Z) - Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling [44.18914219393549]
We study how agents can learn world models with representations that are task-specific, minimal, and sufficient for decision-making.<n>We achieve this via a closed-loop synergy between the agent and the world model.
arXiv Detail & Related papers (2026-07-05T17:02:40Z) - Making Foresight Actionable: Repurposing Representation Alignment in World Action Models [57.23863557252883]
World Action Models (WAMs) offer a promising route for robot manipulation by using video generation models to model future scene evolution.<n> generating plausible visual futures does not always guarantee the extraction of accurate actions.<n>We propose AGRA, an Action-Grounded Representation Alignment objective.
arXiv Detail & Related papers (2026-06-10T15:31:25Z) - DisCo: World Models with Discrete Camera Motion Control [79.86256515640231]
We propose DisCo, a controllable video world model that conditions generation on a compact set of discrete action primitives to improve action separability.<n>DisCo achieves significantly more reliable action following while preserving visual quality.
arXiv Detail & Related papers (2026-06-06T03:50:45Z) - WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation [56.5415838759151]
WBench is a comprehensive benchmark for evaluation of interactive world models.<n>It covers video quality, setting adherence, interaction adherence, consistency, and physics compliance.<n>It contains 289 test cases and 1,058 interaction turns, covering diverse scenes, styles, subjects, and both first- and third-person perspectives.
arXiv Detail & Related papers (2026-05-25T14:01:31Z) - iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework [27.208236690012914]
iWorld-Bench is a benchmark for training and testing world models on interaction-related abilities.<n>We construct a diverse dataset with 330k video clips and select 2.1k high-quality samples covering varied perspectives, weather, and scenes.
arXiv Detail & Related papers (2026-05-05T16:30:03Z) - WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models [114.95269118652163]
We introduce WorldArena, a unified benchmark designed to evaluate embodied world models across both perceptual and functional dimensions.<n>WorldArena assesses models through three dimensions: video perception quality, measured with 16 metrics across six sub-dimensions; embodied task functionality, which evaluates world models as data engines, policy evaluators, and action planners integrating with subjective human evaluation.<n>Through extensive experiments on 14 representative models, we reveal a significant perception-functionality gap, showing that high visual quality does not necessarily translate into strong embodied task capability.
arXiv Detail & Related papers (2026-02-09T18:09:20Z) - ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction [35.24704057622881]
Embodied cognition argues that intelligence arises from sensorimotor interaction rather than passive observation.<n>We introduce ENACT, a benchmark that casts evaluation of embodied cognition as world modeling from egocentric interaction.
arXiv Detail & Related papers (2025-11-26T00:06:02Z) - Object-Centric World Models for Causality-Aware Reinforcement Learning [13.063093054280946]
We propose emph Transformer Imagination with CAusality-aware reinforcement learning (ASTICA)<n>A unified framework in which object-centric Transformers serve as the world model and causality-aware policy and value networks.<n>Experiments on object-rich benchmarks demonstrate that STICA consistently outperforms state-of-the-art agents in both sample efficiency and final performance.
arXiv Detail & Related papers (2025-11-18T08:53:09Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.