Peer-to-Peer Network Technologies

Últimos artículos

• MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks

  Keru Chen, Sen Lin, Yingbin Liang, Nathaniel D. Bastian, Shaofeng Zou · 25 de septiembre de 2026

  Decentralized LLM-based multi-agent systems coordinate through local interactions, but an agent can remain responsive while its task-solving quality persistently degrades. Such gray failures require protecting current tasks before sufficient evidence exists to alter future routing, while still allow…

• Enrich-Retrieve-Rank: Scaling Capability Discovery Beyond In-Context Routing

  Nazib Sorathiya, Daniel Zhang, Bardiya Akhbari · 25 de agosto de 2026

  Agent ecosystems now include thousands of MATS components (Models, Agents, Tools, and Skills), yet their discovery still relies on in-context routing. These systems read a registry (names, hints, or descriptions, as context budget permits), pick a candidate, invoke it, and retry on failure. This pat…

• Hierarchical Server Architecture for Agentic Science

  Vanessa Sochat, Daniel Milroy · 7 de agosto de 2026

  Agentic science is transforming the landscape of computational work, extending to scientific pipelines and workload managers. The workloads require specialized hardware within and across institutions. If assessing workload needs against environments is required for scheduling, automated discovery of…

• HEAL: Resilient and Self-* Hub-based Learning

  Mohamed Amine Legheraba (NPA), Stefan Galkiewicz (NPA), Maria Gradinariu Potop-Butucaru (NPA), S\'ebastien Tixeuil (NPA, IUF, LINCS) · 28 de mayo de 2026

  Decentralized learning enhances privacy, scalability, and fault tolerance by distributing data and computation across nodes. A popular approach is Federated learning, which relies on a central aggregator, yet faces challenges such as server vulnerabilities, scalability issues, privacy risks and most…

• Trade-offs in Decentralized Agentic AI Discovery Across the Compute Continuum

  Patrizio Dazzi, Emanuele Carlini, Matteo Mordacchini, Saul Urso · 13 de mayo de 2026

  Agentic systems deployed across the compute continuum need discovery mechanisms that remain effective across cloud, edge, and intermittently connected domains. In some emerging agentic architectures, decentralized discovery is already an active design direction, placing DHT-based lookup on the path …

• Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing

  Taotao Wang, Lizhao You, Jingwen Tong, Chonghe Zhao, Shengli Zhang · 5 de marzo de 2026

  The ongoing shift of AI models from centralized cloud APIs to local AI agents on edge devices is enabling \textit{Client-Side Autonomous Agents (CSAAs)} -- persistent personal agents that can plan, access local context, and invoke tools on behalf of users. As these agents begin to collaborate by del…

• AgentHub: A Registry for Discoverable, Verifiable, and Reproducible AI Agents

  Erik Pautsch, Tanmay Singla, Parv Kumar, Wenxin Jiang, Huiyun Peng, Behnaz Hassanshahi, Konstantin L\"aufer, George K. Thiruvathukal, James C. Davis · 27 de febrero de 2026

  LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software package registries (e.g., npm) and model hubs (e.g., Hugging Face). Existing efforts typically address naming, distributio…

• Routing, Cascades, and User Choice for LLMs

  Rafid Mahmood · 11 de febrero de 2026

  To mitigate the trade-offs between performance and costs, LLM providers route user tasks to different models based on task difficulty and latency. We study the effect of LLM routing with respect to user behavior. We propose a game between an LLM provider with two models (standard and reasoning) and …

• Cost-Aware Contrastive Routing for LLMs

  Reza Shirkavand, Shangqian Gao, Peiran Yu, Heng Huang · 28 de octubre de 2025

  We study cost-aware routing for large language models across diverse and dynamic pools of models. Existing approaches often overlook prompt-specific context, rely on expensive model profiling, assume a fixed set of experts, or use inefficient trial-and-error strategies. We introduce Cost-Spectrum Co…