From Perception to Action: An Interactive Benchmark for Vision Reasoning

TL;DR

This paper introduces CHAIN, an interactive benchmark for evaluating vision models' ability to understand and act within physical environments, highlighting current models' limitations in reasoning about structure and causality.

Contribution

The paper presents CHAIN, a novel physics-based, interactive benchmark for assessing vision models' reasoning and planning capabilities in dynamic, structured environments.

Findings

State-of-the-art models struggle with physical structure understanding.

Models have difficulty planning long-horizon actions.

Current models cannot reliably translate perception into effective actions.

Abstract

Understanding the physical structure is essential for real-world applications such as embodied agents, interactive design, and long-horizon manipulation. Yet, prevailing Vision-Language Model (VLM) evaluations still center on structure-agnostic, single-turn setups (e.g., VQA), which fail to assess agents' ability to reason about how geometry, contact, and support relations jointly constrain what actions are possible in a dynamic environment. To address this gap, we introduce the Causal Hierarchy of Actions and Interactions (CHAIN) benchmark, an interactive 3D, physics-driven testbed designed to evaluate whether models can understand, plan, and execute structured action sequences grounded in physical constraints. CHAIN shifts evaluation from passive perception to active problem solving, spanning tasks such as interlocking mechanical puzzles and 3D stacking and packing. We conduct a comprehensive study of state-of-the-art VLMs and diffusion-based models under unified interactive settings. Our results show that top-performing models still struggle to internalize physical structure and causal constraints, often failing to produce reliable long-horizon plans and cannot robustly translate perceived structure into effective actions. The project is available at https://social-ai-studio.github.io/CHAIN/.