AgentComm-Bench: Stress-Testing Cooperative Embodied AI Under Latency, Packet Loss, and Bandwidth Collapse
Not on the map. Why?
Abstract (arXiv)
Cooperative multi-agent methods for embodied AI are almost universally evaluated under idealized communication: zero latency, no packet loss, and unlimited bandwidth. Real-world deployment on robots with wireless links, autonomous vehicles on congested networks, or drone swarms in contested spectrum offers no such guarantees. We introduce AgentComm-Bench, a benchmark suite and evaluation protocol that systematically stress-tests cooperative embodied AI under six communication impairment dimensions: latency, packet loss, bandwidth collapse, asynchronous updates, stale memory, and conflicting sensor evidence. AgentComm-Bench spans three task families: cooperative perception, multi-agent waypoint navigation, and cooperative zone search, and evaluates five communication strategies, including a lightweight method we propose based on redundant message coding with staleness-aware fusion. Our experiments reveal that communication-dependent tasks degrade catastrophically: stale memory and bandwidth collapse cause over 96% performance drops in navigation, while content corruption (stale or conflicting data) reduces perception F1 by over 85%. Vulnerability depends on the interaction between impairment type and task design; perception fusion is robust to packet loss but amplifies corrupted data. Redundant message coding more than doubles navigation performance under 80% packet loss. We release AgentComm-Bench as a practical evaluation protocol and recommend that cooperative embodied AI work report performance under multiple impairment conditions.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 18 Mar 2026.
Builds on
29 of 43 references.
References · 29
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
- 2016Learning Multiagent Communication with Backpropagationcited by 366
- 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
- 2021OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communicationcited by 304
- 2020V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Predictioncited by 292
- 2022DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 273
- 2022Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Mapscited by 255
- 2023Building Cooperative Embodied Agents Modularly with Large Language Modelscited by 237
- 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 228
- 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
- 2018TarMAC: Targeted Multi-Agent Communicationcited by 208
- 2019Multi-Agent Pathfinding: Definitions, Variants, and Benchmarkscited by 199
17 more
- 2021Learning Distilled Collaboration Graph for Multi-Agent Perceptioncited by 194
- 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 172
- 2020When2com: Multi-Agent Perception via Communication Graph Groupingcited by 157
- 2022V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Drivingcited by 157
- 2023V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perceptioncited by 155
- 2022Robust Collaborative 3D Object Detection in Presence of Pose Errorscited by 129
- 2020Who2com: Collaborative Perception via Learnable Handshake Communicationcited by 127
- 2018Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Taskscited by 121
- 2019Learning to Schedule Communication in Multi-agent Reinforcement Learningcited by 93
- 2023Collaboration Helps Camera Overtake LiDAR in 3D Detectioncited by 81
- 2019Learning Efficient Multi-agent Communication: An Information Bottleneck Approachcited by 61
- 2022V2XP-ASG: Generating Adversarial Scenes for Vehicle-to-Everything Perceptioncited by 28
- 2023Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Explorationcited by 18
- 2023Context-aware Communication for Multi-agent Reinforcement Learningcited by 13
- 2021Multi-agent Bayesian Deep Reinforcement Learning for Microgrid Energy Management under Communication Failurescited by 5
- 2025Robust and Efficient Communication in Multi-Agent Reinforcement Learningcited by 2
- 2025MAPPO for Edge Server Monitoringcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.