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

arXiv: https://arxiv.org/abs/2607.14103 · HTML: https://mlsanity.com/paper/2607.14103/

## Key facts

- Cited by 1 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 16 references that are in the map.
- First posted on arXiv 6 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/)
- Mechanistic interpretability / [SAE features and their applications](https://mlsanity.com/mechinterp/sae-features-and-their-applications/)

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

- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [Understanding image representations by measuring their equivariance and equivalence](https://mlsanity.com/paper/1411.5908/) (2014)
- [The Unreasonable Ineffectiveness of the Deeper Layers](https://mlsanity.com/paper/2403.17887/) (2024)
- [Emerging Cross-lingual Structure in Pretrained Language Models](https://mlsanity.com/paper/1911.01464/) (2019)
- [Offline bilingual word vectors, orthogonal transformations and the inverted softmax](https://mlsanity.com/paper/1702.03859/) (2017)
- [Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog](https://mlsanity.com/paper/1706.08502/) (2017)
- [Overcoming Data Scarcity in Biomedical Imaging with a Foundational Multi-Task Model](https://mlsanity.com/paper/2311.09847/) (2023)

## Built on by (most cited first, 1 of 1)

- [Post-Hoc Sparse Coding of Latent Communication Between Vision-Language Model Agents](https://mlsanity.com/paper/2608.10198/) (2026)

## Abstract (arXiv)

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.