World Reasoning Arena

• URL: http://arxiv.org/abs/2603.25887v1
• Date: Thu, 26 Mar 2026 20:22:52 GMT
• Title: World Reasoning Arena
• Abstract summary: WR-Arena is a benchmark for evaluating world models along three fundamental dimensions of next world simulation.<n>We build a task taxonomy and curate diverse datasets designed to probe these capabilities.<n>Our results expose a substantial gap between current models and human-level hypothetical reasoning.
• Score: 36.28720055069025
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: World models (WMs) are intended to serve as internal simulators of the real world that enable agents to understand, anticipate, and act upon complex environments. Existing WM benchmarks remain narrowly focused on next-state prediction and visual fidelity, overlooking the richer simulation capabilities required for intelligent behavior. To address this gap, we introduce WR-Arena, a comprehensive benchmark for evaluating WMs along three fundamental dimensions of next world simulation: (i) Action Simulation Fidelity, the ability to interpret and follow semantically meaningful, multi-step instructions and generate diverse counterfactual rollouts; (ii) Long-horizon Forecast, the ability to sustain accurate, coherent, and physically plausible simulations across extended interactions; and (iii) Simulative Reasoning and Planning, the ability to support goal-directed reasoning by simulating, comparing, and selecting among alternative futures in both structured and open-ended environments. We build a task taxonomy and curate diverse datasets designed to probe these capabilities, moving beyond single-turn and perceptual evaluations. Through extensive experiments with state-of-the-art WMs, our results expose a substantial gap between current models and human-level hypothetical reasoning, and establish WR-Arena as both a diagnostic tool and a guideline for advancing next-generation world models capable of robust understanding, forecasting, and purposeful action. The code is available at https://github.com/MBZUAI-IFM/WR-Arena.

Related papers

• Flow Matching in Feature Space for Stochastic World Modeling [21.159664319255665]
  We propose FlowWM, a world model that performs flow matching directly within pretrained feature space.<n>This is challenging because pretrained features are substantially high-dimensional, making standard diffusion recipes suboptimal.<n>We evaluate FlowWM on two benchmarks: a synthetic benchmark for systematic evaluation of accuracy and diversity, and a real-world benchmark FuturePerception.
  arXiv  Detail & Related papers  (2026-06-27T19:35:27Z)
• Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond [209.35045331678043]
  We introduce a "levels x laws" taxonomy organized along two axes.<n>The first defines three capability levels: L1 Predictor, which learns one-step local transition operators; L2 Simulator, which composes them into multi-step, action-conditioned rollouts that respect domain laws; and L3 Evolver, which autonomously revises its own model when predictions fail against new evidence.<n>We synthesize over 400 works and summarize more than 100 representative systems spanning model-based reinforcement learning, video generation, web and GUI agents, multi-agent social simulation, and AI-driven scientific discovery.
  arXiv  Detail & Related papers  (2026-04-24T17:48:47Z)
• ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation [66.02142169323521]
  Vision-Language-Action models and world models have recently emerged as promising paradigms for general-purpose robotic intelligence.<n>Existing benchmarks are largely simulator-centric, which provide controllability but fail to capture the reality gap caused by perception noise.<n>We introduce ManipArena, a standardized evaluation framework designed to bridge simulation and real-world execution.
  arXiv  Detail & Related papers  (2026-03-30T15:06:41Z)
• Causal World Modeling for Robot Control [56.31803788587547]
  Video world models provide the ability to imagine the near future by understanding the causality between actions and visual dynamics.<n>We introduce LingBot-VA, an autoregressive diffusion framework that learns frame prediction and policy execution simultaneously.<n>We evaluate our model on both simulation benchmarks and real-world scenarios, where it shows significant promise in long-horizon manipulation, data efficiency in post-training, and strong generalizability to novel configurations.
  arXiv  Detail & Related papers  (2026-01-29T17:07:43Z)
• Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models [13.90532093512575]
  We propose Imagine-then-Plan (textttITP), a unified framework for agent learning via lookahead imagination.<n>We introduce a novel adaptive lookahead mechanism by trading off the ultimate goal and task progress.<n>Our experiments show that textttITP significantly outperforms competitive baselines.
  arXiv  Detail & Related papers  (2026-01-13T19:49:58Z)
• SimScale: Learning to Drive via Real-World Simulation at Scale [45.08991279559151]
  We introduce a novel and scalable simulation framework capable of synthesizing massive unseen states upon existing driving logs.<n>Our pipeline utilizes advanced neural rendering with a reactive environment to generate high-fidelity multi-view observations.<n>We develop a pseudo-expert trajectory generation mechanism for these newly simulated states to provide action supervision.
  arXiv  Detail & Related papers  (2025-11-28T17:17:38Z)
• FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AI [24.545163508739943]
  FreeAskWorld is an interactive simulation framework that integrates large language models for high-level behavior planning and semantically grounded interaction.<n>Our framework supports scalable, realistic human-agent simulations and includes a modular data generation pipeline tailored for diverse embodied tasks.<n>We present and publicly release FreeAskWorld, a large-scale benchmark dataset comprising reconstructed environments, six diverse task types, 16 core object categories, 63,429 annotated sample frames, and more than 17 hours of interaction data.
  arXiv  Detail & Related papers  (2025-11-17T15:58:46Z)
• A Comprehensive Survey on World Models for Embodied AI [14.457261562275121]
  Embodied AI requires agents that perceive, act, and anticipate how actions reshape future world states.<n>This survey presents a unified framework for world models in embodied AI.
  arXiv  Detail & Related papers  (2025-10-19T07:12:32Z)
• One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration [77.8436947454471]
  Symbolic world modeling requires inferring and representing an environment's transitional dynamics as an executable program.<n>OneLife is a framework that models world dynamics through conditionally-activated programmatic laws.<n>OneLife can successfully learn key environment dynamics from minimal, unguided interaction.
  arXiv  Detail & Related papers  (2025-10-14T02:49:32Z)
• Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation [54.3628937181904]
  Internal world models (WMs) enable agents to understand the world's state and predict transitions.<n>Recent large Vision-Language Models (VLMs), such as OpenAI o3, GPT-4o and Gemini, exhibit potential as general-purpose WMs.
  arXiv  Detail & Related papers  (2025-06-27T03:24:29Z)
• A Survey of World Models for Autonomous Driving [55.520179689933904]
  Recent breakthroughs in autonomous driving have been propelled by advances in robust world modeling.<n>World models offer high-fidelity representations of the driving environment that integrate multi-sensor data, semantic cues, and temporal dynamics.<n>Future research must address key challenges in self-supervised representation learning, multimodal fusion, and advanced simulation.
  arXiv  Detail & Related papers  (2025-01-20T04:00:02Z)
• Predictive World Models from Real-World Partial Observations [66.80340484148931]
  We present a framework for learning a probabilistic predictive world model for real-world road environments. While prior methods require complete states as ground truth for learning, we present a novel sequential training method to allow HVAEs to learn to predict complete states from partially observed states only.
  arXiv  Detail & Related papers  (2023-01-12T02:07:26Z)

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.