# A Token/KV-Cache Communication Media Selection and Resource Allocation Strategy for Multi-Agent Collaboration

arXiv: https://arxiv.org/abs/2605.25422 · HTML: https://mlsanity.com/paper/2605.25422/

## Key facts

- Cited by 2 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 18 of its 30 references that are in the map.
- First posted on arXiv 25 May 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 18 of 18)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Latent Collaboration in Multi-Agent Systems](https://mlsanity.com/paper/2511.20639/) (2025)
- [QAQ: Quality Adaptive Quantization for LLM KV Cache](https://mlsanity.com/paper/2403.04643/) (2024)
- [Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2502.14321/) (2025)
- [Enabling Agents to Communicate Entirely in Latent Space](https://mlsanity.com/paper/2511.09149/) (2025)
- [Thought Communication in Multiagent Collaboration](https://mlsanity.com/paper/2510.20733/) (2025)
- [Overview of AI and Communication for 6G Network: Fundamentals, Challenges, and Future Research Opportunities](https://mlsanity.com/paper/2412.14538/) (2024)
- [Compute Or Load KV Cache? Why Not Both?](https://mlsanity.com/paper/2410.03065/) (2024)
- [DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference](https://mlsanity.com/paper/2602.21548/) (2026)
- [Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems](https://mlsanity.com/paper/2602.03695/) (2026)
- [Q-KVComm: Efficient Multi-Agent Communication Via Adaptive KV Cache Compression](https://mlsanity.com/paper/2512.17914/) (2025)
- [Towards Wireless Native Big AI Model: The Mission and Approach Differ From Large Language Model](https://mlsanity.com/paper/2412.09041/) (2024)
- [Efficient LLM Inference over Heterogeneous Edge Networks with Speculative Decoding](https://mlsanity.com/paper/2510.11331/) (2025)
- [Distributed On-Device LLM Inference With Over-the-Air Computation](https://mlsanity.com/paper/2502.12559/) (2025)
- [When Intelligence Overloads Infrastructure: A Forecast Model for AI-Driven Bottlenecks](https://mlsanity.com/paper/2511.07265/) (2025)
- [FAS-LLM: Large Language Model-Based Channel Prediction for OTFS-Enabled Satellite-FAS Links](https://mlsanity.com/paper/2505.09751/) (2025)

## Built on by (most cited first, 2 of 2)

- [From Semantic to Token Communication: The Next Paradigm for Large-Model-Driven 6G Intelligent Connectivity](https://mlsanity.com/paper/2609.10714/) (2026)
- [Hybrid Reasoning Agents](https://mlsanity.com/paper/2610.18861/) (2026)

## Abstract (arXiv)

The convergence of large language models (LLMs) with 6G networks is fostering a paradigm of autonomous multi-agent cooperation, which in turn is expected to substantially increase east-west traffic. Although latent-space interaction mechanisms can enable more efficient collaboration than symbolic natural-language (NL) exchanges, prior work often abstracts away the associated communication overhead under practical wireless constraints. In embodied multi-agent settings, heterogeneous interaction media incur disparate inference and transmission costs, thereby inducing an inherent end-to-end (E2E) latency trade-off. To address this, we propose a joint design that integrates communication-media selection with wireless resource allocation. Through analytical characterization and simulation-based evaluation, we show that neither token-based transmission nor key-value (KV) cache-based transmission is uniformly optimal across operating regimes, as performance depends critically on system parameters such as available computational resources and channel conditions. Accordingly, we formulate a joint optimization problem aimed at minimizing the E2E latency of multi-agent collaboration and develop a low-complexity joint media selection and resource allocation (JMSRA) algorithm. Numerical results further confirm that, by adaptively coordinating the interaction media and bandwidth allocation over heterogeneous links, the proposed scheme achieves markedly reduced E2E latency relative to conventional NL-only and KV-cache-only baselines, enabling efficient and robust multi-agent collaboration in future wireless networks.