# CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Device

arXiv: https://arxiv.org/abs/2410.09407 · HTML: https://mlsanity.com/paper/2410.09407/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 16 of its 38 references that are in the map.
- First posted on arXiv 12 Oct 2024.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 16 of 16)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [LongNet: Scaling Transformers to 1,000,000,000 Tokens](https://mlsanity.com/paper/2307.02486/) (2023)
- [AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning](https://mlsanity.com/paper/2406.11200/) (2024)
- [Octopus: On-device language model for function calling of software APIs](https://mlsanity.com/paper/2404.01549/) (2024)
- [Octo-planner: On-device Language Model for Planner-Action Agents](https://mlsanity.com/paper/2406.18082/) (2024)
- [Squid: Long Context as a New Modality for Energy-Efficient On-Device Language Models](https://mlsanity.com/paper/2408.15518/) (2024)

## Built on by (most cited first, 6 of 6)

- [Large Language Models for Planning: A Comprehensive and Systematic Survey](https://mlsanity.com/paper/2505.19683/) (2025)
- [HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce Assistants](https://mlsanity.com/paper/2506.19846/) (2025)
- [Chengyu-Bench: Benchmarking Large Language Models for Chinese Idiom Understanding and Use](https://mlsanity.com/paper/2506.18105/) (2025)
- [ConQuer: A Framework for Concept-Based Quiz Generation](https://mlsanity.com/paper/2503.14662/) (2025)
- [OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction](https://mlsanity.com/paper/2604.25602/) (2026)
- [Working with Agentic `Teammates': When a New Organizational Actor Collides with the Human Ecosystem of Work](https://mlsanity.com/paper/2609.29901/) (2026)

## Abstract (arXiv)

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.