Enabling Agents to Communicate Entirely in Latent Space

• URL: http://arxiv.org/abs/2511.09149v1
• Date: Thu, 13 Nov 2025 01:36:00 GMT
• Title: Enabling Agents to Communicate Entirely in Latent Space
• Authors: Zhuoyun Du, Runze Wang, Huiyu Bai, Zouying Cao, Xiaoyong Zhu, Bo Zheng, Wei Chen, Haochao Ying,
• Abstract summary: We propose Interlat (Inter-agent Latent Space Communication), a paradigm that leverages the last hidden states of an LLM as a representation of its mind for direct transmission.<n>An additional compression process further compresses latent communication via entirely latent space reasoning.<n>Experiments demonstrate that Interlat outperforms both fine-tuned chain-of-thought (CoT) prompting and single-agent baselines.
• Score: 19.98668682094137
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While natural language is the de facto communication medium for LLM-based agents, it presents a fundamental constraint. The process of downsampling rich, internal latent states into discrete tokens inherently limits the depth and nuance of information that can be transmitted, thereby hindering collaborative problem-solving. Inspired by human mind-reading, we propose Interlat (Inter-agent Latent Space Communication), a paradigm that leverages the last hidden states of an LLM as a representation of its mind for direct transmission (termed latent communication). An additional compression process further compresses latent communication via entirely latent space reasoning. Experiments demonstrate that Interlat outperforms both fine-tuned chain-of-thought (CoT) prompting and single-agent baselines, promoting more exploratory behavior and enabling genuine utilization of latent information. Further compression not only substantially accelerates inference but also maintains competitive performance through an efficient information-preserving mechanism. We position this work as a feasibility study of entirely latent space inter-agent communication, and our results highlight its potential, offering valuable insights for future research.

Related papers

• InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs [72.5651722107621]
  InterAgent is an end-to-end framework for text-driven physics-based multi-agent humanoid control.<n>We introduce an autoregressive diffusion transformer equipped with multi-stream blocks, which decouples proprioception, exteroception, and action to cross-modal interference.<n>We also propose a novel interaction graph exteroception representation that explicitly captures fine-grained joint-to-joint spatial dependencies.
  arXiv  Detail & Related papers  (2025-12-08T10:46:01Z)
• Thought Communication in Multiagent Collaboration [17.374295882257577]
  We introduce a new paradigm, thought communication, which enables agents to interact directly mind-to-mind, akin to telepathy.<n>We prove that, in a nonparametric setting without auxiliary information, both shared and private latent thoughts between any pair of agents can be identified.<n>We develop a framework that extracts latent thoughts from all agents prior to communication and assigns each agent the relevant thoughts, along with their sharing patterns.
  arXiv  Detail & Related papers  (2025-10-23T16:48:02Z)
• Learning to Interact in World Latent for Team Coordination [53.51290193631586]
  This work presents a novel representation learning framework, interactive world latent (IWoL), to facilitate team coordination in multi-agent reinforcement learning (MARL)<n>Our key insight is to construct a learnable representation space that jointly captures inter-agent relations and task-specific world information by directly modeling communication protocols.<n>Our representation can be used not only as an implicit latent for each agent, but also as an explicit message for communication.
  arXiv  Detail & Related papers  (2025-09-29T22:13:39Z)
• Multimodal Fusion with LLMs for Engagement Prediction in Natural Conversation [70.52558242336988]
  We focus on predicting engagement in dyadic interactions by scrutinizing verbal and non-verbal cues, aiming to detect signs of disinterest or confusion. In this work, we collect a dataset featuring 34 participants engaged in casual dyadic conversations, each providing self-reported engagement ratings at the end of each conversation. We introduce a novel fusion strategy using Large Language Models (LLMs) to integrate multiple behavior modalities into a multimodal transcript''
  arXiv  Detail & Related papers  (2024-09-13T18:28:12Z)
• Bidirectional Emergent Language in Situated Environments [4.950411915351642]
  We introduce two novel cooperative environments: Multi-Agent Pong and Collectors. optimal performance requires the emergence of a communication protocol, but moderate success can be achieved without one. We find that the emerging communication is sparse, with the agents only generating meaningful messages and acting upon incoming messages in states where they cannot succeed without coordination.
  arXiv  Detail & Related papers  (2024-08-26T21:25:44Z)
• Building Cooperative Embodied Agents Modularly with Large Language Models [104.57849816689559]
  We address challenging multi-agent cooperation problems with decentralized control, raw sensory observations, costly communication, and multi-objective tasks instantiated in various embodied environments. We harness the commonsense knowledge, reasoning ability, language comprehension, and text generation prowess of LLMs and seamlessly incorporate them into a cognitive-inspired modular framework. Our experiments on C-WAH and TDW-MAT demonstrate that CoELA driven by GPT-4 can surpass strong planning-based methods and exhibit emergent effective communication.
  arXiv  Detail & Related papers  (2023-07-05T17:59:27Z)
• Over-communicate no more: Situated RL agents learn concise communication protocols [78.28898217947467]
  It is unclear how to design artificial agents that can learn to effectively and efficiently communicate with each other. Much research on communication emergence uses reinforcement learning (RL) We explore situated communication in a multi-step task, where the acting agent has to forgo an environmental action to communicate. We find that while all tested pressures can disincentivise over-communication, situated communication does it most effectively and, unlike the cost on effort, does not negatively impact emergence.
  arXiv  Detail & Related papers  (2022-11-02T21:08:14Z)
• Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents [83.52684405389445]
  We introduce the collaborative multi-object navigation task CoMON. In this task, an oracle agent has detailed environment information in the form of a map. It communicates with a navigator agent that perceives the environment visually and is tasked to find a sequence of goals. We show that the emergent communication can be grounded to the agent observations and the spatial structure of the 3D environment.
  arXiv  Detail & Related papers  (2021-10-12T06:56:11Z)
• Emergent Discrete Communication in Semantic Spaces [3.2280079436668996]
  We propose a neural agent architecture that enables agents to communicate via discrete tokens derived from a learned, continuous space. We show in a decision theoretic framework that our technique optimize communication over a wide range of scenarios, whereas one-hot tokens are only optimal under restrictive assumptions. In self-play experiments, we validate that our trained agents learn to cluster tokens in semantically-meaningful ways, allowing them communicate in noisy environments.
  arXiv  Detail & Related papers  (2021-08-04T03:32:48Z)
• Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning [36.468498804251574]
  We show that discrete message communication has performance comparable to continuous message communication. We propose an approach that allows humans to interactively send discrete messages to agents.
  arXiv  Detail & Related papers  (2021-02-24T20:44:14Z)
• Emergence of Pragmatics from Referential Game between Theory of Mind Agents [64.25696237463397]
  We propose an algorithm, using which agents can spontaneously learn the ability to "read between lines" without any explicit hand-designed rules. We integrate the theory of mind (ToM) in a cooperative multi-agent pedagogical situation and propose an adaptive reinforcement learning (RL) algorithm to develop a communication protocol.
  arXiv  Detail & Related papers  (2020-01-21T19:37:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.