S-Agent 2.0: Spatial Reasoning with a General Coding Agent

Rui Gong, Ruoyu Wang, Yalun Dai, Hao Li, Sidi Yang, Qihao Zhao, Hongyu Li, Zeyang Guan · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28354 · open-access PDF

Hindi

अंतरिक्ष तर्क एक मॉडल को यह पता लगाने के लिए कहता है कि वस्तुएं 3 डी अंतरिक्ष में कहां हैं, वे एक दूसरे से कैसे संबंधित हैं, और वे कैसे आंदोलन करते हैं। एजेंटिक VLMs ने हाल ही में ऐसे कार्यों पर बड़े सुधार लाए हैं, जिससे मॉडल को सक्रिय रूप से 3 डी धारणा उपकरणों के साथ सबूत इकट्ठा करने के बजाय एक ही पास में जवाब देने की अनुमति मिलती है।

Machine translation (Meta M2M100); the English original follows.

Abstract

Spatial reasoning asks a model to work out where objects are in 3D space, how they relate to one another, and how they move. Agentic VLMs have recently brought large improvements on such tasks by letting the model actively gather evidence with 3D perception tools instead of answering in a single pass. Even so, on many questions the tools return the right evidence and the model still does not arrive at the correct answer: the gap between model and tools, where raw readings become usable conclusions, is left unfilled. We present S-Agent 2.0, a spatial reasoning agent that equips an off-the-shelf

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28354, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange