CVPR 2026 accepted papers on Multi-agent systems and games
60 of the 4,042 papers accepted at CVPR 2026 (1.5%) are on Multi-agent systems and games, compared with 0.9% at CVPR 2025. They fall into 4 topics.
See CVPR 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
LLM agents · 29 papers
- See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles (1 citation)
- Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery Detection
- AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
- Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos
- EpiAgent: An Agent-Centric System for Ancient Inscription Restoration
- Experience Transfer for Multimodal LLM Agents in Minecraft Game
- Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs
- GUI-CEval: A Hierarchical and Comprehensive Chinese Benchmark for Mobile GUI Agents
- HATS: Hardness-Aware Trajectory Synthesis for GUI Agents
- HiconAgent: History Context-aware Policy Optimization for GUI Agents
- Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning
- Hybrid Agents for Image Restoration
and 17 more in the interactive map.
Human-AI and goal-conditioned · 25 papers
- SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation (1 citation)
- Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning
- AstraNav-Memory: Contexts Compression for Long Memory
- CATNet: Collaborative Alignment and Transformation Network for Cooperative Perception
- Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models
- CoLC: Communication-Efficient Collaborative Perception with LiDAR Completion
- Dejavu: Towards Experience Feedback Learning for Embodied Intelligence
- Demo2Tutorial: From Human Experience to Multimodal Software Tutorials
- Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs
- IPR-1: Interactive Physical Reasoner
- MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping
- NitroGen: An Open Foundation Model for Generalist Gaming Agents
and 13 more in the interactive map.
Cooperative multi-agent RL · 5 papers
- InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs
- VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning
- Beyond Rule-Based Agents: Active Markov Games for Realistic Multi-Agent Interaction in Autonomous Driving
- MangoBench: A Benchmark for Multi-Agent Goal-Conditioned Offline Reinforcement Learning
- TaskForce: Cooperative Multi-agent Reinforcement Learning for Multi-task Optimization