CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making
cs.AI
Submitted: 2026-05-02
Updated: 2026-09-21
Comments: 27 pages. Substantially revised manuscript with updated methodology, experiments, theoretical analysis, figures, and references
Code: https://github.com/Guowei-Zou/coflow
Project page: https://guowei-zou.github.io/coflow
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- OM2P: Offline Multi-Agent Mean-Flow Policy
- Mean Flows for One-step Generative Modeling
- Improved Mean Flows: On the Challenges of Fastforward Generative Models
- SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling
- IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
- The TerraByte Client: providing access to terabytes of plant data
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- The StarCraft Multi-Agent Challenge
- DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation
- OGPO: One-Step Generative Policy Optimization for Real-Time Robot Control
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection