Summary of Camphor: Collaborative Agents For Multi-input Planning and High-order Reasoning on Device, by Yicheng Fu et al.
CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Device
by Yicheng Fu, Raviteja Anantha, Jianpeng Cheng
First submitted to arxiv on: 12 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces CAMPHOR, a novel on-device Small Language Model (SLM) multi-agent framework designed to handle multiple user inputs and reason over personal context locally. CAMPHOR employs a hierarchical architecture that decomposes complex tasks and coordinates expert agents responsible for personal context retrieval, tool interaction, and dynamic plan generation. The framework reduces model size, latency, and memory usage by implementing parameter sharing across agents and leveraging prompt compression. Experiments reveal that fine-tuned SLM agents surpass closed-source Large Language Models (LLMs) in task completion F1 by 35%, eliminating the need for server-device communication while enhancing privacy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new way to make computers understand what we want them to do, using small language models. These small models are good at understanding and responding to our requests, but they have limitations when it comes to complex tasks. The researchers developed a new framework called CAMPHOR that helps these small models work together to accomplish more complicated tasks. This approach reduces the amount of data and energy needed for the computers to process our requests. The results show that this method is better than others at completing tasks, while also keeping personal information private. |
Keywords
» Artificial intelligence » Language model » Prompt
