用压缩的键值缓存代替文本传递，让大模型代理通信更快更省资源。
Q-KVComm: Efficient Multi-Agent Communication Via Adaptive KV Cache Compression
- 直接传输压缩后的键值缓存，避免重复计算上下文。
- 实现5-6倍压缩率，语义保真度高于0.77。
- 适配不同模型规模，适合多代理问答与复杂推理场景。
多代理大语言模型系统面临关键瓶颈：代理间冗余的上下文信息传输消耗大量带宽和计算资源。传统方法丢弃内部语义表示，仅传输原始文本，导致接收代理需从头重新计算相似表示。我们提出Q-KVComm协议，实现大语言模型代理间压缩键值（KV）缓存的直接传输。该协议融合三项核心创新：(1) 基于敏感性分析的自适应分层量化，按层分配可变位宽；(2) 混合信息提取机制，跨内容领域保留关键事实；(3) 异构模型校准，支持跨架构通信。在三个多样化问答数据集上的实验表明，Q-KVComm在保持语义保真度的前提下实现5-6倍压缩比，所有场景下连贯性得分均高于0.77。该协议在模型规模1.1B-1.5B参数范围内表现稳健，适用于对话问答与多跳推理等真实应用。本工作建立了大模型代理通信的新范式，推动信息交换从文本导向转向表示导向。
原文摘要 · Abstract (English)
Multi-agent Large Language Model (LLM) systems face a critical bottleneck: redundant transmission of contextual information between agents consumes excessive bandwidth and computational resources. Traditional approaches discard internal semantic representations and transmit raw text, forcing receiving agents to recompute similar representations from scratch. We introduce Q-KVComm, a new protocol that enables direct transmission of compressed key-value (KV) cache representations between LLM agents. Q-KVComm combines three key innovations: (1) adaptive layer-wise quantization that allocates variable bit-widths based on sensitivity profiling, (2) hybrid information extraction that preserves critical facts across content domains, and (3) heterogeneous model calibration establishing cross-architecture communication. Extensive experiments across three diverse question-answering datasets demonstrate that Q-KVComm achieves 5-6x compression ratios while maintaining semantic fidelity, with coherence quality scores above 0.77 across all scenarios. The protocol exhibits robust performance across model sizes (1.1B-1.5B parameters) and adapts to real-world applications including conversational QA and multi-hop reasoning. Our work establishes a new paradigm for LLM agent communication, shifting from text-based to representation-based information exchange.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。