Multi Agent

Multi Agent

15 bookmarks
Newest
Structured Test-Time Scaling: From Multi-Agent Systems to General Inference Architectures
Structured Test-Time Scaling: From Multi-Agent Systems to General Inference Architectures
A unified theoretical framework for structured test-time scaling, showing how topology compression, scope isolation, and decoupled verification—a three-layer structural decoupling—bypass the linear collapse of long-horizon reasoning across multi-agent systems, recursive architectures, and coding agents.
·xinmingtu.cn·
Structured Test-Time Scaling: From Multi-Agent Systems to General Inference Architectures
Diagrid - Durable Workflows for AI Agents
Diagrid - Durable Workflows for AI Agents
An overview of four durable agentic patterns, from deterministic workflows to autonomous multi-agent orchestration, and the trade-offs each architecture introduces.
·diagrid.io·
Diagrid - Durable Workflows for AI Agents
Cognition | Don’t Build Multi-Agents
Cognition | Don’t Build Multi-Agents
Frameworks for LLM Agents have been surprisingly disappointing. I want to offer some principles for building agents based on our own trial & error, and explain why some tempting ideas are actually quite bad in practice.
·cognition.ai·
Cognition | Don’t Build Multi-Agents
A Multi-Agent Framework for Synthetic Data Generation
A Multi-Agent Framework for Synthetic Data Generation
Presents MAG-V, a multi-agent framework that first generates a dataset of questions that mimic customer queries. It then reverse engineer alternate questions from responses to verify agent trajectories. Reports that the… — elvis (@omarsar0)
·x.com·
A Multi-Agent Framework for Synthetic Data Generation