# See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents

arXiv: https://arxiv.org/abs/2606.13594 · HTML: https://mlsanity.com/paper/2606.13594/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2026.

## Built on by (most cited first, 8 of 8)

- [KV Cache Translation across Heterogeneous Large Language Models](https://mlsanity.com/paper/2607.28979/) (2026)
- [When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs](https://mlsanity.com/paper/2608.04893/) (2026)
- [KV-Lingo: Learning KV-Cache Translators with Distillation](https://mlsanity.com/paper/2609.32610/) (2026)
- [Unified AI Gateway: A Framework for Joint Model Routing and KV Cache Management](https://mlsanity.com/paper/2609.06940/) (2026)
- [Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs](https://mlsanity.com/paper/2609.32259/) (2026)
- [Draft-KV: Learning Useful Latent Communication Between Language Models](https://mlsanity.com/paper/2609.34754/) (2026)
- [Principled Thoughts for Latent Recursive LLM Systems](https://mlsanity.com/paper/2609.36159/) (2026)
- [Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families](https://mlsanity.com/paper/2610.15095/) (2026)

## Abstract (arXiv)

Multi-agent systems communicate mostly through text, paying a lossy and expensive decode and re-encode cost. KV-cache communication is a promising alternative, yet most prior work is homogeneous, using duplicate copies of the same model, and avoids the central challenge of cross-model latent alignment; existing heterogeneous methods are also restrictive, typically assuming shared input and using transferred caches mainly for steering. We study a more fundamental question: can heterogeneous agents be aligned well enough to perform real "mind reading" and transfer both what one agent sees and how it thinks? Our information-structure analysis reveals a duality: context-aware transfer is driven by sparse reasoning signals, while context-unaware transfer, where the receiver sees no input, requires dense contextual knowledge preservation. Motivated by this, we propose dense alignment for heterogeneous KV-cache communication via a lightweight cross-model cache transformation and two-phase training: reconstruction followed by generation. Across all six directions of {Qwen3-4B, 8B, 14B} and six in-domain and out-of-domain benchmarks, our method outperforms prior heterogeneous baselines, matches or exceeds text communication in context-aware settings at roughly 2 to 3 times lower compute, and remains effective in context-unaware transfer where prior methods collapse.