# Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models

arXiv: https://arxiv.org/abs/2610.19696 · HTML: https://mlsanity.com/paper/2610.19696/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 22 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Builds on (most cited first, 20 of 20)

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [Relative representations enable zero-shot latent space communication](https://mlsanity.com/paper/2209.15430/) (2022)
- [Verbalizable Representations Form a Global Workspace in Language Models](https://mlsanity.com/paper/2607.15495/) (2026)
- [Latent Collaboration in Multi-Agent Systems](https://mlsanity.com/paper/2511.20639/) (2025)
- [SelfIE: Self-Interpretation of Large Language Model Embeddings](https://mlsanity.com/paper/2403.10949/) (2024)
- [Cache-to-Cache: Direct Semantic Communication Between Large Language Models](https://mlsanity.com/paper/2510.03215/) (2025)
- [Let Models Speak Ciphers: Multiagent Debate through Embeddings](https://mlsanity.com/paper/2310.06272/) (2023)
- [Transferring Linear Features Across Language Models With Model Stitching](https://mlsanity.com/paper/2506.06609/) (2025)
- [Communicating Activations Between Language Model Agents](https://mlsanity.com/paper/2501.14082/) (2025)
- [XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication](https://mlsanity.com/paper/2608.11676/) (2026)
- [Dual-Cache Latent Space Communication between Heterogeneous Language Models](https://mlsanity.com/paper/2608.20617/) (2026)
- [J-CoT: Chain-of-Thought in J-Space](https://mlsanity.com/paper/2607.21981/) (2026)
- [Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model](https://mlsanity.com/paper/2607.20058/) (2026)
- [Beyond Token-Level Guidance: Inference-Time Alignment of Specialized LLMs via Cross-Family Representation Steering](https://mlsanity.com/paper/2608.30319/) (2026)

## Abstract (arXiv)

Multi-agent systems allow language models to solve tasks collaboratively by sharing complementary information. These systems typically communicate through text, while recent approaches also explore exchanging internal model states. However, sharing these states across architectures often requires learned translators or assumptions about model compatibility. We introduce SYNC (Symbol-Indexed Neural Communication), a word-indexed interface that connects heterogeneous models without fine-tuning or a learned translator. From descriptions only it can see, the sender selects words from a shared list and sends their indices for each object, without seeing the questions. The receiver writes the described facts into its hidden states using its own word directions, vectors fitted once from its activations. We test selective use by swapping one attribute between two objects and requiring correct answers about both changed and unchanged attributes before and after the swap, four answers in total. We choose an early write layer on four development receivers and then fix it. With three different senders and nine newer receivers from five families, four-answer success on new scenes reaches 72.0-98.3%, up to 96 percentage points above middle-layer writing, and the two largest receivers match plain text. A task-free probe predicted in advance which depths each new receiver can use (45 of 45 cases). Without retuning, messages listing every fact keep 89.6-100% success under new layouts, and sender messages reach 23.9-64.0% on a landmark task with multi-token symbols, below text but from 0% without a message. These results show that shared word indices and receiver-local directions can support selective fact use across model families without additional training.