{"ID":3084856,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T05:00:38.846751169Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05711","arxiv_id":"2606.05711","title":"Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems","abstract":"Multi-agent systems built on large language models (LLMs) have become a prevailing paradigm for tackling complex reasoning, planning, and tool-use tasks. The dominant communication protocol in such systems is natural language: agents exchange messages token-by-token, verbalising their internal reasoning so that peers can read, verify, and respond. While convenient and interpretable, this protocol suffers from three structural drawbacks -- high inference cost, irreversible information loss during discretization, and ambiguity/redundancy of natural language. A growing body of work therefore explores an alternative protocol -- latent communication -- in which agents exchange continuous representations (embeddings, hidden states, or KV-caches) directly, bypassing the bottleneck of text generation. This paper presents a unified framework for organising the rapidly expanding literature on latent communication. We analyse existing methods along three orthogonal axes: (1) WHAT information is communicated (Embeddings, Hidden States, KV-Caches, or other continuous state); (2) WHICH sender-receiver alignment is used (latent-space alignment and layer alignment); and (3) HOW the communicated information is fused into the receiver (concatenation, prepending, mathematical operations, cross-attention, or cache restoration). Under this 3-axis framework, we systematically categorise eighteen representative methods proposed between 2024 and 2026, identify five major design patterns, and surface a set of open challenges -- including cross-architecture alignment, security of latent channels, compression for edge deployment, and the relationship between latent communication and latent chain-of-thought. We hope that this framework both lowers the barrier to entry for new researchers and provides a vocabulary for comparing future work.","short_abstract":"Multi-agent systems built on large language models (LLMs) have become a prevailing paradigm for tackling complex reasoning, planning, and tool-use tasks. The dominant communication protocol in such systems is natural language: agents exchange messages token-by-token, verbalising their internal reasoning so that peers c...","url_abs":"https://arxiv.org/abs/2606.05711","url_pdf":"https://arxiv.org/pdf/2606.05711v1","authors":"[\"Yingzhuo Liu\"]","published":"2026-06-04T05:10:20Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}