XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication

• URL: http://arxiv.org/abs/2608.11676v1
• Date: Wed, 12 Aug 2026 05:32:33 GMT
• Title: XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication
• Abstract summary: Heterogeneous multi-agent LLM systems can outperform homogeneous configurations by reducing redundant reasoning patterns.<n>Existing communication protocols either operate through text, discarding the sender's internal representations, or require architectural homogeneity for latent-level transfer.<n>We identify the entity grounding problem in cross-architecture communication: cross-attention bridges that transfer continuous representations across different LLM families suffer from rare-token compression collapse.<n>We propose XBRIDGE, a decode-free communication protocol that addresses this through two mechanisms.
• Score: 41.12003897083975
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redundant reasoning patterns. Yet existing communication protocols either operate through text, discarding the sender's internal representations, or require architectural homogeneity for latent-level transfer. We identify the entity grounding problem in cross-architecture communication: cross-attention bridges that transfer continuous representations across different LLM families suffer from rare-token compression collapse, where entity identity is lost in the continuous bottleneck (bridge-only F1 ~30%). We propose XBRIDGE, a decode-free communication protocol that addresses this through two mechanisms. Lexical Anchor Mapping (LAM) maps the sender's original context tokens to the receiver's vocabulary, providing discrete entity anchors. A Latent Enrichment Bridge (LEB) lets the receiver query the sender's hidden states for contextual enrichment. The entity anchors ground the bridge's contextual signals to specific entities through the receiver's own self-attention. Across three model families (Llama, Qwen, and Mistral), seven benchmarks, and both communication directions, XBRIDGE outperforms text-based communication on all seven tasks for each model pair while achieving 11x lower latency, and in a same-architecture setting it also exceeds a KV-sharing baseline on six of seven tasks. LEB requires only 264M trainable parameters (3.8% of the receiver), is trained on a small balanced sample set, and adds negligible inference overhead.

Related papers

• From Semantic to Token Communication: The Next Paradigm for Large-Model-Driven 6G Intelligent Connectivity [94.51565447227847]
  6G networks are driving communication systems from reliable bit delivery toward meaning-aware and task-oriented connectivity.<n>Large models (LMs) with strong multimodal understanding and generation capabilities have accelerated this shift.<n>Current LM-driven semantic communication (SemCom) remains fragmented.<n>We argue that tokens provide a natural candidate for this missing abstraction.
  arXiv  Detail & Related papers  (2026-09-09T18:11:38Z)
• UEmbed: Unified Sparse and Dense Multimodal Embeddings [56.1131203949042]
  We introduce UEmbed, a decoder-only multimodal embedding model.<n>It produces both sparse lexical and dense representations in one causal forward pass.<n>We train UEmbed at 2B, 4B, and 9B scales, and it outperforms multimodal embedding models trained on publicly available data.<n>Overall, UEmbed offers a new paradigm: it unifies dense and sparse embeddings in one model, while further extending sparse retrieval to unify text and multimodal inputs.
  arXiv  Detail & Related papers  (2026-08-03T17:54:11Z)
• HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning [27.564924459355424]
  We propose textscHiComm, a plug-in communication module that grounds messages in the sender's hierarchical observation.<n>textscHiComm is receiver-driven, and the hierarchy is resolved through a three-stage decoding process.<n>Experiments show that textscHiComm matches or outperforms representative learned communication baselines while reducing communication volume by up to $23times$ per receiver per episode.
  arXiv  Detail & Related papers  (2026-06-28T00:29:12Z)
• 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)
• Neural Router: Semantic Content Matching for Agentic AI [41.39228253084888]
  Large language models (LLMs) can serve as the semantic-matching engine of a content-based publish/subscribe broker for agentic AI.<n> Framed as offline multi-label retrieval over three public datasets, our central contribution is a two-crossover cost-accuracy characterisation.
  arXiv  Detail & Related papers  (2026-05-25T10:58:53Z)
• 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)
• TeleEmbedBench: A Multi-Corpus Embedding Benchmark for RAG in Telecommunications [2.2508462342902633]
  Large language models (LLMs) are increasingly deployed in the telecommunications domain for critical tasks.<n>We introduce TeleEmbedBench, the first large-scale, multi-corpus embedding benchmark designed specifically for telecommunications.
  arXiv  Detail & Related papers  (2026-04-20T04:00:13Z)
• WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference [56.297697169678095]
  WISV (Wireless-Informed Semantic Verification) is a novel distributed speculative decoding framework.<n>We show that WISV achieves up to a 60.8% increase in accepted length, a 37.3% reduction in interaction rounds, and a 31.4% improvement in end-to-end latency.<n>We validate WISV on a hardware testbed comprising an NVIDIA Jetson AGX Orin and an A40-equipped server.
  arXiv  Detail & Related papers  (2026-04-20T01:29:56Z)
• GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems [55.12339141172908]
  GoAgent is a communication topology generation method that explicitly treats collaborative groups as the atomic units of MAS construction.<n>Experiments on six benchmarks demonstrate the state-of-the-art performance of GoAgent with 93.84% average accuracy while reducing token consumption by about 17%.
  arXiv  Detail & Related papers  (2026-03-20T06:21:32Z)
• 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)
• Spatial Semantic Recurrent Mining for Referring Image Segmentation [63.34997546393106]
  We propose Stextsuperscript2RM to achieve high-quality cross-modality fusion. It follows a working strategy of trilogy: distributing language feature, spatial semantic recurrent coparsing, and parsed-semantic balancing. Our proposed method performs favorably against other state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2024-05-15T00:17:48Z)

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.