#Multi-agent (6)

LoopX is an open, provider-neutral, stateful control plane that runs on top of Codex, Claude Code, Cursor and other agent harnesses instead of replacing them. It preserves objectives, gates, todos, scope, evidence, quota and handoffs as durable state across turns, restarts and agents, and uses quota to decide whether a loop may continue, keeping multi-day work reviewable, restartable and handoff-able.

Agent infrastructureControl planeLong-horizon agents

Python5.7k50427

Graph Engineering: The Complete Guide to Building Multi-Agent AI Systems

The hard problem in multi-agent systems is not making one agent smarter, but deciding how work itself should move. This long-form guide introduces Graph Engineering: use the dependency test to expose fake dependencies, measure latency by critical path instead of total steps, compress deterministically before reasoning, give verifiers a falsification objective, model human approval as an edge rather than a node, freeze rules that sit outside optimization, and adopt five canonical graph shapes plus a paste-ready graph spec template — along with clear criteria for when NOT to build a graph at all.

BLOG

Multi-agentGraph engineeringOrchestrationLLMAgent orchestration

0:08

Marope: multi-agent RL for robot rope jumping

@ErenChenAI · 81 views · 2026-08-12

MaropeLAMDAMulti-Agent RL

1:17

Multi-Agent CAD: text-to-3D open source

@xyz2maureen · 71 views · 2026-08-06

CADMulti-agent3D Generation

Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learning

In multi-agent reinforcement learning (MARL), inter-agent communication is effective for improving performance under partial observability. Representation learning-based approaches enable decentralized agents to learn messages grounded in their own observations, but they rely only on current observations and cannot convey information accumulated over time. We propose Dreamer-CPC, a decentralized model-based MARL method that integrates message learning based on Collective Predictive Coding (CPC) into the world model of DreamerV3. Each agent independently maintains a world model and a message module, and infers and exchanges messages from the latent states of the world model that reflect the history of past observations and actions. We evaluated Dreamer-CPC in two environments: Observer, a non-cooperative information-sharing task, and CatchApple, a newly introduced task in which task-relevant observations are temporarily missing. In both environments, Dreamer-CPC outperformed IPPO-CPC, an existing CPC-based method that generates messages from current observations, as well as no-communication baselines. In particular, in CatchApple, Dreamer-CPC achieved 4 to 5 times the episode return of IPPO-CPC, demonstrating effective coordination where other methods fail due to missing observations. These results suggest that communication grounded in the latent dynamics of world models can support decentralized decision-making when current observations alone are insufficient.

Taisuke Takayama, Naoto Yoshida, Tadahiro TaniguchiJul 22, 2026

DreamerWorld ModelsMulti-agentJul 22, 2026

Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers

Multi-agent interactive world models should not only generate consistent observations, but also maintain world states that persist across agents and evolve across views. Existing autoregressive video diffusion pipelines carry forward observation history as conditioning context, which makes shared state difficult to maintain in multi-agent and multi-view settings. We present WorldWeaver (W^2), a streaming multi-agent video diffusion model that augments rollout with cross-agent world state registers: learnable tokens that store shared world information, track individual agent status, and are dynamically updated after each generated chunk. We ground these registers with supervision signals spanning individual agent status, global state views including bird's-eye views, and scene text. We further improve the architecture with a Mixture-of-Transformers design that uses separate weights for world state modeling and visual frame modeling. Extensive experiments in two-agent Minecraft video generation show that explicit world-state modeling improves logical consistency and generation quality.

Sicheng Mo, Yuheng Li, Ziyang LengJul 23, 2026

World ModelsMulti-agentDiffusion modelsJul 23, 2026