# Communicating Activations Between Language Model Agents

arXiv: https://arxiv.org/abs/2501.14082 · HTML: https://mlsanity.com/paper/2501.14082/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 23 Jan 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 24 of 24)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Towards Expert-Level Medical Question Answering with Large Language Models](https://mlsanity.com/paper/2305.09617/) (2023)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://mlsanity.com/paper/1706.05125/) (2017)
- [Linearity of Relation Decoding in Transformer Language Models](https://mlsanity.com/paper/2308.09124/) (2023)
- [Relative representations enable zero-shot latent space communication](https://mlsanity.com/paper/2209.15430/) (2022)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM](https://mlsanity.com/paper/2403.07816/) (2024)
- [Learning to Decode Collaboratively with Multiple Language Models](https://mlsanity.com/paper/2403.03870/) (2024)
- [Word-order biases in deep-agent emergent communication](https://mlsanity.com/paper/1905.12330/) (2019)
- [Translating Neuralese](https://mlsanity.com/paper/1704.06960/) (2017)
- [Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought](https://mlsanity.com/paper/2404.03414/) (2024)

## Built on by (most cited first, 16 of 16)

- [Enabling Agents to Communicate Entirely in Latent Space](https://mlsanity.com/paper/2511.09149/) (2025)
- [KVComm: Enabling Efficient LLM Communication through Selective KV Sharing](https://mlsanity.com/paper/2510.03346/) (2025)
- [Augmenting Multi-Agent Communication with State Delta Trajectory](https://mlsanity.com/paper/2506.19209/) (2025)
- [The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems](https://mlsanity.com/paper/2602.15382/) (2026)
- [Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems](https://mlsanity.com/paper/2606.05711/) (2026)
- [Multi-Way Representation Alignment](https://mlsanity.com/paper/2602.06205/) (2026)
- [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)
- [XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication](https://mlsanity.com/paper/2608.11676/) (2026)
- [The Bicameral Model: Bidirectional Hidden-State Coupling Between Parallel Language Models](https://mlsanity.com/paper/2605.11167/) (2026)
- [Hard or Just Unreached? Diagnosing the Sampling Blind Spot in Math-Reasoning Difficulty Estimation](https://mlsanity.com/paper/2606.19636/) (2026)
- [Large Language Models Do Not Always Need Readable Language](https://mlsanity.com/paper/2606.19857/) (2026)
- [Receiver-Conditioned Latent Communication gives 94% CacheBack](https://mlsanity.com/paper/2609.32046/) (2026)
- [Social Circuits behind Multi-agent Echo Chambers](https://mlsanity.com/paper/2609.34444/) (2026)
- [Draft-KV: Learning Useful Latent Communication Between Language Models](https://mlsanity.com/paper/2609.34754/) (2026)
- [Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models](https://mlsanity.com/paper/2610.19696/) (2026)

## Abstract (arXiv)

Communication between multiple language model (LM) agents has been shown to scale up the reasoning ability of LMs. While natural language has been the dominant medium for inter-LM communication, it is not obvious this should be the standard: not only does natural language communication incur high inference costs that scale quickly with the number of both agents and messages, but also the decoding process abstracts away too much rich information that could be otherwise accessed from the internal activations. In this work, we propose a simple technique whereby LMs communicate via activations; concretely, we pause an LM textitB's computation at an intermediate layer, combine its current activation with another LM textitA's intermediate activation via some function textitf, then pass textitf's output into the next layer of textitB and continue the forward pass till decoding is complete. This approach scales up LMs on new tasks with zero additional parameters and data, and saves a substantial amount of compute over natural language communication. We test our method with various functional forms textitf on two experimental setups--multi-player coordination games and reasoning benchmarks--and find that it achieves up to 27.0% improvement over natural language communication across datasets with <1/4 the compute, illustrating the superiority and robustness of activations as an alternative "language" for communication between LMs.