CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Device
This addresses the problem of latency and privacy for on-device AI applications, though it appears incremental as it builds on existing multi-agent and SLM concepts.
The paper tackled the challenge of deploying small language models (SLMs) on devices for multi-input planning and reasoning while maintaining privacy, resulting in a framework that improved task completion F1 by about 35% compared to closed-source LLMs and eliminated server-device communication.
While server-side Large Language Models (LLMs) demonstrate proficiency in function calling and complex reasoning, deploying Small Language Models (SLMs) directly on devices brings opportunities to improve latency and privacy but also introduces unique challenges for accuracy and memory. We introduce CAMPHOR, an innovative on-device SLM multi-agent framework designed to handle multiple user inputs and reason over personal context locally, ensuring privacy is maintained. CAMPHOR employs a hierarchical architecture where a high-order reasoning agent decomposes complex tasks and coordinates expert agents responsible for personal context retrieval, tool interaction, and dynamic plan generation. By implementing parameter sharing across agents and leveraging prompt compression, we significantly reduce model size, latency, and memory usage. To validate our approach, we present a novel dataset capturing multi-agent task trajectories centered on personalized mobile assistant use-cases. Our experiments reveal that fine-tuned SLM agents not only surpass closed-source LLMs in task completion F1 by~35\% but also eliminate the need for server-device communication, all while enhancing privacy.