Augmenting Multi-Agent Communication with State Delta Trajectory

• URL: http://arxiv.org/abs/2506.19209v2
• Date: Wed, 24 Sep 2025 02:27:14 GMT
• Title: Augmenting Multi-Agent Communication with State Delta Trajectory
• Authors: Yichen Tang, Weihang Su, Yujia Zhou, Yiqun Liu, Min Zhang, Shaoping Ma, Qingyao Ai,
• Abstract summary: 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.
• Score: 44.68954502805962
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Multi-agent techniques such as role playing or multi-turn debates have been shown to be effective in improving the performance of large language models (LLMs) in downstream tasks. Despite their differences in workflows, existing multi-agent systems constructed from a single base LLM mostly use natural language for agent communication. While this is appealing for its simplicity and interpretability, it also introduces inevitable information loss as one model must down sample its continuous state vectors to discrete tokens before transferring them to the other model. Such losses are particularly significant when the information to transfer is not simple facts, but reasoning logics or abstractive thoughts. To tackle this problem, we propose a new communication protocol that transfers both natural language tokens and token-wise state transition trajectory from one agent to another. Particularly, compared to the actual state value, we find that the sequence of state changes in LLMs after generating each token can better reflect the information hidden behind the inference process. We propose a State Delta Encoding (SDE) method to represent state transition trajectories. The experimental results show that multi-agent systems with SDE achieve SOTA performance compared to other communication protocols, particularly in tasks that involve complex reasoning.

Related papers

• Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation [50.22481337087162]
  Referring Video Object (RVOS) aims to segment objects in videos based on textual queries.<n>Refer-Agent is a collaborative multi-agent system with alternating reasoning-reflection mechanisms.
  arXiv  Detail & Related papers  (2026-02-03T14:48:12Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• Reasoning-Aware Prompt Orchestration: A Foundation Model for Multi-Agent Language Model Coordination [0.0]
  We present a theoretically-grounded framework for dynamic prompt orchestration that enhances reasoning across multiple specialized agents.<n>This framework addresses three core challenges: logical consistency preservation during agent transitions, reasoning-aware prompt adaptation, and scalable coordination of distributed inference.<n> Experimental results on 1,000 synthetic multi-agent conversations demonstrate a 42% reduction in reasoning latency, a 23% improvement in logical consistency measured by ROUGE-L score, and an 89% success rate for task completion without context loss.
  arXiv  Detail & Related papers  (2025-09-30T22:33:01Z)
• Token Communication in the Era of Large Models: An Information Bottleneck-Based Approach [55.861432910722186]
  UniToCom is a unified token communication paradigm that treats tokens as the fundamental units for both processing and wireless transmission.<n>We propose a generative information bottleneck (GenIB) principle, which facilitates the learning of tokens that preserve essential information.<n>We employ a causal Transformer-based multimodal large language model (MLLM) at the receiver to unify the processing of both discrete and continuous tokens.
  arXiv  Detail & Related papers  (2025-07-02T14:03:01Z)
• Concept-Level AI for Telecom: Moving Beyond Large Language Models [1.7922382138350863]
  Large Language Models (LLMs) can be effectively applied to certain telecom problems.<n>But due to their inherent token-by-token processing and limited capacity for maintaining extended context, LLMs struggle to fulfill telecom-specific requirements.<n>This paper argues that adopting LCMs is not simply an incremental step, but a necessary evolutionary leap toward achieving robust and effective AI-driven telecom management.
  arXiv  Detail & Related papers  (2025-06-27T16:20:18Z)
• LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation [102.1527101235251]
  LangTraj is a language-conditioned scene-diffusion model that simulates the joint behavior of all agents in traffic scenarios.<n>By conditioning on natural language inputs, LangTraj provides flexible and intuitive control over interactive behaviors.<n>LangTraj demonstrates strong performance in realism, language controllability, and language-conditioned safety-critical simulation.
  arXiv  Detail & Related papers  (2025-04-15T17:14:06Z)
• Cooperative Multi-Agent Planning with Adaptive Skill Synthesis [16.228784877899976]
  We present a novel multi-agent architecture that integrates vision-language models (VLMs) with a dynamic skill library and structured communication for decentralized closed-loop decision-making.<n>The skill library, bootstrapped from demonstrations, evolves via planner-guided tasks to enable adaptive strategies.<n>We demonstrate its strong performance against state-of-the-art MARL baselines across both symmetric and asymmetric scenarios.
  arXiv  Detail & Related papers  (2025-02-14T13:23:18Z)
• Virgo: A Preliminary Exploration on Reproducing o1-like MLLM [89.50691075011429]
  Slow-thinking reasoning systems have garnered widespread attention by scaling the thinking time during inference.<n>There is also growing interest in adapting this capability to multimodal large language models (MLLMs)<n>In this paper, we explore a straightforward approach by fine-tuning a capable MLLM with a small amount of textual long-form thought data.<n>We find that these long-form reasoning processes, expressed in natural language, can be effectively transferred to MLLMs.
  arXiv  Detail & Related papers  (2025-01-03T17:14:16Z)
• SpeechAgents: Human-Communication Simulation with Multi-Modal Multi-Agent Systems [53.94772445896213]
  Large Language Model (LLM)-based multi-agent systems have demonstrated promising performance in simulating human society. We propose SpeechAgents, a multi-modal LLM based multi-agent system designed for simulating human communication.
  arXiv  Detail & Related papers  (2024-01-08T15:01:08Z)
• Let Models Speak Ciphers: Multiagent Debate through Embeddings [84.20336971784495]
  We introduce CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. By deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs.
  arXiv  Detail & Related papers  (2023-10-10T03:06:38Z)
• Simultaneous Machine Translation with Large Language Models [51.470478122113356]
  We investigate the possibility of applying Large Language Models to SimulMT tasks. We conducted experiments using the textttLlama2-7b-chat model on nine different languages from the MUST-C dataset. The results show that LLM outperforms dedicated MT models in terms of BLEU and LAAL metrics.
  arXiv  Detail & Related papers  (2023-09-13T04:06:47Z)
• Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems [27.39706173574983]
  Transferring the knowledge of large language models (LLMs) is a promising technique to incorporate linguistic knowledge into end-to-end automatic speech recognition (ASR) systems. We show that transferring multiple representations of LLMs can be an effective alternative to transferring only a single representation.
  arXiv  Detail & Related papers  (2023-09-07T21:57:39Z)
• Large AI Model Empowered Multimodal Semantic Communications [48.73159237649128]
  We propose a Large AI Model-based Multimodal SC (LAMMSC) framework. We first present the Conditional-based Multimodal Alignment (MMA) that enables the transformation between multimodal and unimodal data. Then, a personalized LLM-based Knowledge Base (LKB) is proposed, which allows users to perform personalized semantic extraction or recovery. Finally, we apply the Generative adversarial network-based channel Estimation (CGE) for estimating the wireless channel state information.
  arXiv  Detail & Related papers  (2023-09-03T19:24:34Z)
• Scalable Communication for Multi-Agent Reinforcement Learning via Transformer-Based Email Mechanism [9.607941773452925]
  Communication can impressively improve cooperation in multi-agent reinforcement learning (MARL) We propose a novel framework Transformer-based Email Mechanism (TEM) to tackle the scalability problem of MARL communication for partially-observed tasks.
  arXiv  Detail & Related papers  (2023-01-05T05:34:30Z)

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.