AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative Reasoning
This work addresses the challenge of generating physically plausible and semantically consistent layouts for applications like virtual environments and home robots, representing a strong specific gain in the domain of automated layout synthesis.
The paper tackles the problem of automated layout generation by proposing AutoLayout, a method that integrates a closed-loop self-validation process within a dual-system framework to mitigate spatial hallucination and balance semantic fidelity with physical plausibility, achieving a 10.1% improvement over state-of-the-art methods in physical plausibility, semantic consistency, and functional completeness across 8 scenarios.
The automated generation of layouts is vital for embodied intelligence and autonomous systems, supporting applications from virtual environment construction to home robot deployment. Current approaches, however, suffer from spatial hallucination and struggle with balancing semantic fidelity and physical plausibility, often producing layouts with deficits such as floating or overlapping objects and misaligned stacking relation. In this paper, we propose AutoLayout, a fully automated method that integrates a closed-loop self-validation process within a dual-system framework. Specifically, a slow system harnesses detailed reasoning with a Reasoning-Reflection-Generation (RRG) pipeline to extract object attributes and spatial constraints. Then, a fast system generates discrete coordinate sets and a topological relation set that are jointly validated. To mitigate the limitations of handcrafted rules, we further introduce an LLM-based Adaptive Relation Library (ARL) for generating and evaluating layouts. Through the implementation of Slow-Fast Collaborative Reasoning, the AutoLayout efficiently generates layouts after thorough deliberation, effectively mitigating spatial hallucination. Its self-validation mechanism establishes a closed-loop process that iteratively corrects potential errors, achieving a balance between physical stability and semantic consistency. The effectiveness of AutoLayout was validated across 8 distinct scenarios, where it demonstrated a significant 10.1% improvement over SOTA methods in terms of physical plausibility, semantic consistency, and functional completeness.