StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems

• URL: http://arxiv.org/abs/2608.13317v1
• Date: Thu, 13 Aug 2026 14:40:59 GMT
• Title: StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems
• Abstract summary: We propose a training-free latent communication approach that aligns the sender's hidden states to the receiver's input space via a closed-form transformation.<n>StateBridge achieves the best or tied-best score on 22 out of 26 model-task pairs.
• Score: 35.74603358195608
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck. Converting the sender's continuous hidden states into discrete tokens discards information that token identities alone cannot capture. Recent work proposes latent communication as an alternative, where agents transmit hidden representations directly without converting them to text. However, existing latent methods either inject working memory layer by layer across the transformers, or require trained projectors that limit portability. We propose StateBridge, a training-free latent communication approach that aligns the sender's final-layer hidden states to the receiver's input space via a closed-form orthogonal transformation. Lightweight norm calibration and vocabulary anchoring ensure compatibility with the pretrained input distribution. The aligned states are prepended to the input of the receiver agent as a continuous prefix. We evaluate StateBridge on math reasoning, code generation, and question answering with four models from two families. StateBridge achieves the best or tied-best score on 22 out of 26 model-task pairs, consistently outperforming the strongest baseline.

Related papers

• Legible-by-Construction: Attention and End-to-End Transformers [0.2663471820643486]
  A transformer's feed-forward layer can be rebuilt from explicit fuzzy set operations.<n> hidden units read as named logical operators at no cost to language-model quality.<n>Across five specialized-attention designs at 125M parameters, 44 to 62 percent of value channels become legible.
  arXiv  Detail & Related papers  (2026-07-05T14:08:59Z)
• Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems [0.65268245109828]
  Multi-agent systems built on large language models (LLMs) have become a prevailing paradigm for tackling complex reasoning, planning, and tool-use tasks.<n>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.<n>A growing body of work therefore explores an alternative protocol -- latent communication, in which agents exchange continuous representations directly, bypassing the bottleneck of text generation.<n>This paper presents a unified framework for organising the rapidly expanding literature on latent communication.
  arXiv  Detail & Related papers  (2026-06-04T05:10:20Z)
• The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models [52.93186090124315]
  We argue that token commitment can be learned as a reusable trace-state policy.<n>We introduce TraceLock, a lightweight plug-in controller that instantiates this policy for a frozen diffusion language model.
  arXiv  Detail & Related papers  (2026-05-23T18:23:46Z)
• Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights [58.27172968382275]
  Multi-agent LLM systems usually collaborate by exchanging natural-language messages.<n>We study an alternative communication interface: instead of appending a sender's message to the receiver's context, compile the sender's hidden states into a transient, receiver-specific weight perturbation.
  arXiv  Detail & Related papers  (2026-05-13T17:58:32Z)
• Bridging Hidden States in Vision-Language Models [0.0]
  Vision-Language Models (VLMs) are a new family of models that align image content with natural language.<n>We propose a lightweight fusion module: a few cross-only, bidirectional attention layers placed near the top of both encoders.<n>The encoders remain non-causal and strong for understanding, while generation stays cleanly decoupled via an optional decoder.
  arXiv  Detail & Related papers  (2025-11-14T17:55:25Z)
• Direct Semantic Communication Between Large Language Models via Vector Translation [3.81908263930559]
  Large language models (LLMs) pass messages as plain tokens, discarding most latent semantics.<n>We form a latent bridge via vector translations, which use learned mappings that enable direct semantic exchange.
  arXiv  Detail & Related papers  (2025-11-06T00:43:29Z)
• Augmenting Multi-Agent Communication with State Delta Trajectory [44.68954502805962]
  We propose a new communication protocol that transfers both natural language tokens and token-wise state transition from one agent to another.<n>We find that the sequence of state changes in LLMs after generating each token can better reflect the information hidden behind the inference process.<n>The experimental results show that multi-agent systems with SDE achieve SOTA performance compared to other communication protocols.
  arXiv  Detail & Related papers  (2025-06-24T00:38:25Z)
• Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration [54.897493351694195]
  We propose a novel parallel decoding approach, namely textithidden transfer, which decodes multiple successive tokens simultaneously in a single forward pass. In terms of acceleration metrics, we outperform all the single-model acceleration techniques, including Medusa and Self-Speculative decoding.
  arXiv  Detail & Related papers  (2024-04-18T09:17:06Z)
• Self-supervised Learning with Random-projection Quantizer for Speech Recognition [51.24368930992091]
  We present a simple and effective self-supervised learning approach for speech recognition. The approach learns a model to predict masked speech signals, in the form of discrete labels. It achieves similar word-error-rates as previous work using self-supervised learning with non-streaming models.
  arXiv  Detail & Related papers  (2022-02-03T21:29:04Z)
• Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
  We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
  arXiv  Detail & Related papers  (2020-10-24T11:55:28Z)

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.