Tag
vLLM introduces Semantic Router, a serving-layer primitive that enables collaboration between multiple models through micro-agents, allowing the router to improve output quality without modifying model weights.
This paper proposes the concept of the world wide AI-Model Network (AI-ModelNet), a novel paradigm for interconnecting, sharing capabilities, and enabling collaborative reasoning among diverse large models. The authors review current single- and multi-model research, present a hierarchical architecture, and validate feasibility through a prototype system and application cases.
This paper introduces a conversational voice agent system that uses a lightweight on-device 'Talker' model to start responding immediately, then incorporates knowledge from a frontier LLM 'Reasoner' as it becomes available, achieving 7-19x faster time-to-first-response while approaching frontier-level performance on a laptop.
This paper introduces scaling participation, a new paradigm for building modular AI systems through contributions from diverse stakeholders, where small models collaborate to outperform monolithic LLMs by up to 15.4% across various tasks, demonstrating emergent capabilities and improved diversity benefits.