摘要：多智能体系统在众多情境与行业中被广泛应用。这些系统依赖智能体间通信，通常通过明文消息传递实现。我们假设，当需要传达复杂概念时，大语言模型可能拥有超越文本表达能力的内部世界模型。本研究旨在通过结构化实验验证这一假设。本工作表明，通过文本通信的LLM智能体会丢失信息，我们通过稀疏自编码器特征分析对这一损失进行了量化。我们构建了三种通信通道，并测量了每种通道中区分概念的信息量。我们首先证明，SAE稀疏通道以28倍压缩比保留99.4%的探测准确率，而密集隐式通道与文本通道分别为80.4%。随后，我们通过稀疏隐空间对齐，检验跨架构通信的同类表现。我们发现，通过Procrustes对齐，Llama和Mistral之间的Top-1检索率达92%。借助文本往返实验，我们进行特征留存分析，发现文本序列化破坏了88%的SAE特征，并代之以不同的特征集。我们将损失归因于特征身份替换而非衰减。根据我们的分析，线性Procrustes对齐导致了3-10个百分点的性能惩罚，非线性对齐方法有所改善。在任务级评估中，我们发现隐式通道在跨语言概念任务上与文本通道表现相当，但从未超越。用隐式特征增强文本并未带来收益，这使我们对初始假设得出否定结论：丢失的特征主要或完全编码表面形式，而非任务相关的语义。要明确隐式通信相对于文本通道的实际优势，需要能够激发复杂概念的更深层任务以及相应的分析框架。

提交历史

来自：Markus Wenzel [

查看邮件

]

[v1]

2026年5月6日周三 13:12:00 UTC (1,547 KB)

[Submitted on 6 May 2026]

Title:Latent Communication Between Language Model Agents: Channels, Alignment, and the Limits of Text

View a PDF of the paper titled Latent Communication Between Language Model Agents: Channels, Alignment, and the Limits of Text, by Markus Wenzel

View PDF HTML (experimental)

Abstract:Multi-agent systems (MAS) are utilized in many contexts and many professions. Those MAS rely on inter-agent communication, usually implemented by clear-text message passing. We hypothesize that Large Language Models may have a world model at their disposal that exceeds expressibility in text when complex concepts need to be communicated. Our aim is to approach a proof of this hypothesis with structured experiments. In this work, we show that LLM agents communicating via text lose information, which we quantify via Sparse Autoencoder (SAE) feature analysis. We construct three communication channels and measure concept-discriminating information in each. We first show that the SAE-sparse channel retains a 99.4% probe accuracy at 28-fold compression over the dense-latent channel vs 80.4% for the text channel. We then proceed to examine the same for cross-architecture communication by using sparse latent space alignment. We find for Procrustes alignment a 92% top-1 retrieval between Llama and Mistral. Using a text round-trip, we perform feature survival analysis to find that text serialization destroys 88% of SAE features, replacing them with a different feature set. We attribute the loss to identity replacement, not attenuation. By our analysis, we were able to attribute a 3-10pp performance penalty to the linear Procrustes alignment, improving with nonlinear alignment methods. In a task-level evaluation we find that the latent channel matches the text channel on cross-lingual concept tasks but never exceeds it. Text augmentation with latent features provides no benefit, leading us to negative conclusions for the initial hypothesis: lost features mostly or completely encode surface form, not task-relevant semantics. To pinpoint the practical advantage of latent communication over a text channel, deeper tasks eliciting complex concepts and an corresponding analysis framework are needed.

Submission history

From: Markus Wenzel [

view email

]

[v1]

Wed, 6 May 2026 13:12:00 UTC (1,547 KB)