3 papers
cs.AI2026
Beyond Rule-Based Workflows: An Information-Flow-Orchestrated Multi-Agents Paradigm via Agent-to-Agent Communication from CORAL
Xinxing Ren, Quagmire Zang, Caelum Forder +5
Most existing Large Language Model (LLM)-based Multi-Agent Systems (MAS) rely on predefined workflows, where human engineers enumerate task states in advance and specify routing ru…
cs.CY2026
Permission Manifests for Web Agents
Samuele Marro, Alan Chan, Xinxing Ren +12
The rise of Large Language Model (LLM)-based web agents represents a significant shift in automated interactions with the web. Unlike traditional crawlers that follow simple conven…
cs.MA2025
Anemoi: A Semi-Centralized Multi-agent System Based on Agent-to-Agent Communication MCP server from Coral Protocol
Xinxing Ren, Caelum Forder, Qianbo Zang +6
Recent advances in generalist multi-agent systems (MAS) have largely followed a context-engineering plus centralized paradigm, where a planner agent coordinates multiple worker age…