# Knowledge Distillation from Language-Oriented to Emergent Communication for Multi-Agent Remote Control

arXiv: https://arxiv.org/abs/2401.12624 · HTML: https://mlsanity.com/paper/2401.12624/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 23 Jan 2024.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)
- Knowledge distillation / [On-policy and self-distillation for LLMs](https://mlsanity.com/distill/on-policy-and-self-distillation-for-llms/)

## Builds on (most cited first, 13 of 13)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving](https://mlsanity.com/paper/2310.03026/) (2023)
- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [A Latent Space Theory for Emergent Abilities in Large Language Models](https://mlsanity.com/paper/2304.09960/) (2023)
- [Language-Oriented Communication with Semantic Coding and Knowledge Distillation for Text-to-Image Generation](https://mlsanity.com/paper/2309.11127/) (2023)
- [Efficient Image Captioning for Edge Devices](https://mlsanity.com/paper/2212.08985/) (2022)
- [Towards Semantic Communication Protocols: A Probabilistic Logic Perspective](https://mlsanity.com/paper/2207.03920/) (2022)
- [WiThRay: A Versatile Ray-Tracing Simulator for Smart Wireless Environments](https://mlsanity.com/paper/2304.11385/) (2023)

## Built on by (most cited first, 3 of 3)

- [AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes](https://mlsanity.com/paper/2506.14728/) (2025)
- [Improving Zero-Shot ObjectNav with Generative Communication](https://mlsanity.com/paper/2408.01877/) (2024)
- [LLM-Empowered Agentic MAC Protocols: A Dynamic Stackelberg Game Approach](https://mlsanity.com/paper/2510.10895/) (2025)

## Abstract (arXiv)

In this work, we compare emergent communication (EC) built upon multi-agent deep reinforcement learning (MADRL) and language-oriented semantic communication (LSC) empowered by a pre-trained large language model (LLM) using human language. In a multi-agent remote navigation task, with multimodal input data comprising location and channel maps, it is shown that EC incurs high training cost and struggles when using multimodal data, whereas LSC yields high inference computing cost due to the LLM's large size. To address their respective bottlenecks, we propose a novel framework of language-guided EC (LEC) by guiding the EC training using LSC via knowledge distillation (KD). Simulations corroborate that LEC achieves faster travel time while avoiding areas with poor channel conditions, as well as speeding up the MADRL training convergence by up to 61.8% compared to EC.