arXiv AI
WorldFailBench: Do World Models Understand Policy Failures?
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Oct 7
RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments
General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities carry into the physical world. To investigate this, we...
arXiv Machine Learning
Jul 17
Active Real-World Factor-Based Evaluation for Generalist Robot Policies
arXiv:2607. 14439v1 Announce Type: new Abstract: Generalist robot manipulation policies trained on large, diverse datasets have shown remarkable promise across a wide range of tasks.
arXiv AI
Sep 30
LIBERO-MAX: Do Robot Policies Adapt When the World Changes?
arXiv:2609.36518v1 Announce Type: cross Abstract: Robots must often continue a task after a target moves, the viewpoint shifts, or an obstacle appears, even though their earlier observations and comm...
arXiv Machine Learning
Oct 8
RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments
arXiv:2610.10409v1 Announce Type: cross Abstract: General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities car...
Hugging Face Trending Papers
Aug 10
WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation
Action-conditioned world models (ACWMs) promise to provide embodied AI with scalable predictive simulators for planning, policy evaluation, and data generation. Realizing this promise requires precise action-conditioned transitions rather than merely plausible outputs.
Hugging Face Trending Papers
Oct 26
Rollback: Experience Backtracking in World Models for Policy Improvement
Action-conditioned world models offer a scalable alternative to costly real-world interaction for improving robot policies. However, existing world-model-based methods largely treat world models as fo...