{"slug": "multi-robot-cooperative-spatial-reasoning-with-multimodal-large-language-models", "title": "Multi-Robot Cooperative Spatial Reasoning with Multimodal Large Language Models", "summary": "Researchers introduced CoopSR, the first benchmark for multi-robot cooperative spatial reasoning, along with the EgoTeam dataset containing 114,227 question-answer pairs across 19 question types. The team also proposed SP-CoR, a multimodal large language model framework that integrates synchronized egocentric videos from multiple robots to answer spatial, temporal, and coordination questions, outperforming the strongest fine-tuned baseline by up to 7.12% in simulated environments. The work advances embodied AI by enabling models to reason cooperatively from multiple robotic viewpoints without requiring privileged pose data at test time.", "body_md": "# Computer Science > Computer Vision and Pattern Recognition\n\n[Submitted on 18 May 2026 (\n\n[v1](https://arxiv.org/abs/2605.18431v1)), last revised 19 May 2026 (this version, v2)]# Title:Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models\n\n[View PDF](/pdf/2605.18431)\n\n[HTML (experimental)](https://arxiv.org/html/2605.18431v2)\n\nAbstract:Multimodal Large Language Models (MLLMs) have made substantial progress in egocentric video understanding, but their ability to reason cooperatively from multiple embodied viewpoints remains largely unexplored. We study this problem through multi-robot cooperative dynamic spatial reasoning, where a model must answer spatial, temporal, visibility, and coordination questions by integrating synchronized egocentric videos from a team of moving robots. To support this setting, we introduce CoopSR, the first benchmark for this task, together with EgoTeam, a multi-robot egocentric QA dataset. EgoTeam contains 114,227 QA pairs spanning 19 question types, four difficulty tiers, and three team sizes in Habitat and iGibson, along with a real-world test set of around 2,326 QAs collected using two quadruped robots. We further propose SP-CoR (Spectral and Physics-Informed Cooperative Reasoner), an MLLM framework for fine-grained cooperative spatial reasoning. SP-CoR combines dynamics-aware multi-robot frame sampling, spectral- and physics-guided view fusion, and physics-aligned prompt distillation, enabling the model to benefit from privileged robot-pose supervision during training while requiring only egocentric videos at test time. Across 22 MLLM baselines, SP-CoR consistently improves cooperative reasoning, outperforming the strongest fine-tuned baseline by +3.87% on Habitat and +7.12% on iGibson. It also shows stronger generalization to unseen team sizes and real-world robot tests. Code can be found at[this https URL].\n\n## Submission history\n\nFrom: Kunyu Peng [[view email](/show-email/a3c8df04/2605.18431)]\n\n**Mon, 18 May 2026 14:04:26 UTC (18,895 KB)**\n\n[[v1]](/abs/2605.18431v1)**[v2]** Tue, 19 May 2026 05:12:41 UTC (18,895 KB)\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/multi-robot-cooperative-spatial-reasoning-with-multimodal-large-language-models", "canonical_source": "https://arxiv.org/abs/2605.18431", "published_at": "2026-06-06 14:04:56+00:00", "updated_at": "2026-06-06 14:19:19.339389+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "robotics", "computer-vision", "ai-research"], "entities": ["CoopSR", "EgoTeam", "SP-CoR", "Habitat", "iGibson"], "alternates": {"html": "https://wpnews.pro/news/multi-robot-cooperative-spatial-reasoning-with-multimodal-large-language-models", "markdown": "https://wpnews.pro/news/multi-robot-cooperative-spatial-reasoning-with-multimodal-large-language-models.md", "text": "https://wpnews.pro/news/multi-robot-cooperative-spatial-reasoning-with-multimodal-large-language-models.txt", "jsonld": "https://wpnews.pro/news/multi-robot-cooperative-spatial-reasoning-with-multimodal-large-language-models.jsonld"}}