Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web

Holos is a web-scale LLM-based multi-agent system designed to address scaling and coordination challenges in AI ecosystems. By introducing a five-layer architecture and the Nuwa engine, it lays the foundation for a self-organizing and evolving Agentic Web.

Computer Science > Artificial Intelligence

Title:Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web

As large language models (LLM)-driven agents transition from isolated task solvers to persistent digital entities, the emergence of the Agentic Web, an ecosystem where heterogeneous agents autonomously interact and co-evolve, marks a pivotal shift toward Artificial General Intelligence (AGI). However, LLM-based multi-agent systems (LaMAS) are hindered by open-world issues such as scaling friction, coordination breakdown, and value dissipation. To address these challenges, we introduce Holos, a web-scale LaMAS architected for long-term ecological persistence. Holos adopts a five-layer architecture, with core modules primarily featuring the Nuwa engine for high-efficiency agent generation and hosting, a market-driven Orchestrator for resilient coordination, and an endogenous value cycle to achieve incentive compatibility. By bridging the gap between micro-level collaboration and macro-scale emergence, Holos hopes to lay the foundation for the next generation of the self-organizing and continuously evolving Agentic Web. We have publicly released Holos, providing a resource for the community and a testbed for future research in large-scale agentic ecosystems.

Source: arXiv cs.AI Recent

More in this category

agentic-systems

VAMPS: Visual-Assisted Mathematical Problem Solving Benchmark

Researchers have introduced VAMPS, a new benchmark designed to evaluate how multimodal large language models leverage visualization tools for mathematical reasoning. The study reveals a surprising gap, showing that models still perform better with direct analytical solving than with tool-enabled visual plotting.

agentic-systems

StepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis

Researchers have introduced StepPRM-RTL, a novel framework combining process-reward modeling (PRM) and Monte Carlo Tree Search (MCTS) to enhance LLM-based RTL code generation. The method improves functional correctness and reasoning fidelity by over 10%, setting a new standard for hardware design automation.

NOW LET US Related – The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents

agentic-systems

The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents

A new study reveals critical flaws in timing interventions on autonomous AI agents, showing that both affect-based triggers and LLM judges fail due to the 'saturation trap' and highly subjective human standards.

EXPLORE TOPICS