Sentinel: Embodied Cooperative Spatial Reasoning and Planning
This paper studies cooperative spatial intelligence for decentralized embodied agents in city-scale outdoor environments, introducing the Sentinel Challenge benchmark and the CoSaR framework that combines foundation model communication with classical navigation algorithms, leading to faster gathering and improved safety.
Article intelligence
Key points
- Introduces Sentinel Challenge where agents must coordinate via natural language to find a meeting point while avoiding dynamic sentinels.
- Proposes CoSaR framework integrating high-level planning of foundation models with precise classical navigation.
- Evaluated on 14 city-scale scenes with 3-5 agents, CoSaR achieves faster convergence and better safety.
- Demonstrates necessity of dynamic communication integrated with spatial reasoning for robust multi-agent cooperation.
Why it matters
This matters because introduces Sentinel Challenge where agents must coordinate via natural language to find a meeting point while avoiding dynamic sentinels.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.26239] Sentinel: Embodied Cooperative Spatial Reasoning and Planning
[Submitted on 25 May 2026]
Title:Sentinel: Embodied Cooperative Spatial Reasoning and Planning
View a PDF of the paper titled Sentinel: Embodied Cooperative Spatial Reasoning and Planning, by Xiangye Lin and 4 other authors
View PDF HTML (experimental)
Abstract:In this work, we study Cooperative Spatial Intelligence, the ability of decentralized embodied agents to coordinate effectively under dynamic environmental constraints across city-scale outdoor domains. We introduce Sentinel Challenge, a benchmark where multiple decentralized embodied agents must communicate in natural language to agree on a mutually safe and convenient meeting point within large, city-scale outdoor environments. Each agent must then navigate safely while avoiding dynamic sentinels patrolling the area, using a tool that provides coarse spatial information. To address this, we propose CoSaR (Cooperative Spatial Reasoning and Planning), a framework that bridges the high-level communication and planning abilities of foundation models with the precision of classical spatial navigation algorithms. CoSaR enables agents to exchange situational updates, reason over evolving spatial constraints, and collaboratively replan trajectories. Evaluated across 14 city-level scenes with 3-5 agents, CoSaR consistently leads to faster gathering, shorter path lengths, and improved safety. Our results demonstrate that integrating dynamic communication with spatial reasoning is essential for robust multi-agent cooperation. By formalizing this new setting and providing a scalable benchmark, we aim to build a foundation for advancing cooperative spatial intelligence in embodied multi-agent systems. Code and challenge are available at this https URL.
Comments: The first two authors contributed equally
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Multiagent Systems (cs.MA)
Cite as: arXiv:2605.26239 [cs.CV]
(or arXiv:2605.26239v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2605.26239
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Hongxin Zhang [view email] [v1] Mon, 25 May 2026 18:04:41 UTC (4,520 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Sentinel: Embodied Cooperative Spatial Reasoning and Planning, by Xiangye Lin and 4 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-05
Change to browse by:
cs cs.MA
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both 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.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)