ChainSpace：面向空间智能的链式推理范式
ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence
- College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）
- Li Auto Inc.（理想汽车有限公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对现有空间推理方法的缺陷，提出ChainSpace链式推理范式，构建对应基准与训练框架，相关模型在基准上表现最优且可迁移至多类外部基准，为空间智能评估与学习提供有效方案。
AI中文摘要：
空间智能要求基础模型在与物理世界的交互过程中维持连贯的空间状态。然而，现有的以数据为中心的方法通常将空间推理视为独立的问答实例，这使得模型能够基于捷径作答，且仅能为持续的空间理解提供有限的监督。为解决这一问题，我们提出了ChainSpace，一种将空间推理构建为状态保留的多轮过程的链式推理范式。在该范式中，空间问题被组织成具有逻辑约束和联合一致性的链，后续问题依赖于前几轮建立的空间约束。遵循这一原则，我们构建了ChainSpace-Bench，这是一个带有链感知指标的人工标注真实世界多轮基准；还构建了ChainSpace-Pipeline，一个基于模拟器的用于空间智能训练的链式结构化监督生成框架。实验表明，ChainSpace-Bench能够发现孤立问题准确率无法捕捉的链级故障。此外，利用相对少量的模拟器生成的链式数据，经ChainSpace-Pipeline训练的模型在ChainSpace-Bench上取得了开源模型中的最佳性能，并可竞争性地迁移到多个外部空间智能基准。这些结果确立了ChainSpace作为一种有效范式，可用于更可靠的空间智能评估和更具数据效率的空间智能学习。
英文摘要：
Spatial intelligence requires foundation models to maintain coherent spatial state across interactions with the physical world. However, existing data-centric approaches typically treat spatial reasoning as independent question-answer instances, enabling shortcut-based answering and providing limited supervision for persistent spatial understanding. To address this, we introduce ChainSpace, a chained-reasoning paradigm that structures spatial reasoning as a state-preserving multi-round process. In this paradigm, spatial questions are organized into logically constrained and jointly consistent chains, where later questions depend on spatial constraints established in earlier rounds. Following this principle, we instantiate ChainSpace-Bench, a manually annotated real-world multi-round benchmark with a Chain-Aware Metric, and ChainSpace-Pipeline, a simulator-based chain-structured supervision generation framework for spatial intelligence training. Experiments show that ChainSpace-Bench exposes chain-level failures that are not captured by isolated question accuracy. Additionally, with a relatively small amount of simulator-generated chained data, models trained by ChainSpace-Pipeline achieve the best performance among open-source models on ChainSpace-Bench and transfer competitively to multiple external spatial intelligence benchmarks. These results establish ChainSpace as an effective paradigm for more faithful evaluation and more data-efficient learning of spatial intelligence.
