AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

SCoT: Teaching 3D-LLMs to Think Spatially with Million-scale CoT Annotations

Jinpeng Li, Haiping Wang, Jiabin chen, Yuan Liu, Zhen Dong, Bisheng Yang

ICLR 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces SCoT, a million-scale chain-of-thought annotation dataset for training 3D-LLMs to reason spatially across perception, reasoning, and planning levels.

Problem

3D-LLM training data typically lack explicit reasoning processes, which limits complex spatial reasoning and task planning in 3D environments.

Approach

Annotates a million-scale chain-of-thought dataset spanning three levels (spatial perception, spatial reasoning, task planning) to supply explicit reasoning supervision for 3D-LLMs.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add CoT supervision to simple perception tasks (ablation)SCoT-Reasoner · SQA3D / ScanQAEM / CIDEr: SQA3D EM 55.8 -> 47.4; ScanQA CIDEr 87.9 -> 73.4Hurt
add CoT supervision to implicit detection (ablation)SCoT-Reasoner · Implicit DetectionAcc@0.25: 8.6 -> 32.2Improved
add CoT supervision to implicit detection (ablation)Chat Scene · Implicit DetectionAcc@0.25: 6.7 -> 26.9Improved
add CoT supervision to analysis and planning (ablation)SCoT-Reasoner · Object AnalysisFaithfulness: 5.59 -> 6.15Improved
add CoT supervision to analysis tasks (ablation)SCoT-Reasoner · Analysis/planning text similarityROUGE-L, METEOR: avg +0.74 ROUGE-L, +0.36 METEORNo clear effect
add CoT supervision to un-situated planning (ablation)Chat Scene · Un-situated PlanningROUGE-L: 27.73 -> 27.24Hurt
keep object-level <SI> tags in CoT (ablation)SCoT-Reasoner · Object AnalysisFaithfulness: 5.37 -> 6.15Improved
keep scene-level <SI> tags in CoT (ablation)SCoT-Reasoner · Situated PlanningTrustworthiness: 6.55 -> 7.14Improved
train on SCoT instead of 3D-R1 dataChat Scene · MSQA-ScanNet zero-shotoverall score: 43.1 -> 47.6Improved
train on SCoT then test zero-shot on ARKitScenesSCoT-Reasoner · MSQA-ARKitScenesoverall score: 41.0 -> 41.2Improved
add CoT supervision to scene analysis (ablation)Chat3D V2 · Scene AnalysisFaithfulness: 6.48 -> 6.43No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy