SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

About this episode

This episode discusses the SpatialClaw framework for enhancing spatial reasoning in vision-language models.

🤗 Upvotes: 80 | cs.CV, cs.AI Authors: Seokju Cho, Ryo Hachiuma, Abhishek Badki, Hang Su, Byung-Kwan Lee, Chan Hee Song, Sifei Liu, Subhashree Radhakrishnan, Seungryong Kim, Yu-Chiang Frank Wang, Min-Hung Chen Title: SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning Arxiv: http://arxiv.org/abs/2606.13673v1 Abstract: Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs). Tool-augmented agents attempt to address this by augmenting VLMs with specialist perception modules, yet their effectiveness is bounded by the action interface through which those tools are invoked. In this work, we study how the design of this interface shapes the agent's capacity for open-ended spatial reasoning. Existing spatial agents either employ single-pass code execution, which commits to a full analysis strategy before any intermediate result is observed, or rely on a structured tool-call interface that often offers less flexibility for freely composing operations or tailoring the analysis to each task. Both designs offer limited flexibility for open-ended, complex…

People in this episode

Hosts: Jingwen Liang, Gengyu Wang

Topics covered

• spatial reasoning
• vision-language models
• tool-augmented agents
• action interface
• 3D reasoning
• complex analysis

Keywords

• spatial reasoning
• vision-language models
• SpatialClaw
• action interface
• 3D analysis
• tool-augmented agents

Mentioned in this episode

Books & works: SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

More episodes of Daily Paper Cast

• EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments · June 13, 2026 · 24 min
• MiniMax Sparse Attention · June 13, 2026 · 26 min
• InterleaveThinker: Reinforcing Agentic Interleaved Generation · June 13, 2026 · 21 min
• FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents · June 13, 2026 · 23 min
• Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? · June 13, 2026 · 20 min
• MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling · June 13, 2026 · 24 min