Augmenting Multi-Agent Communication with State Delta Trajectory

Yichen Tang, Weihang Su, Yujia Zhou, Yiqun Liu, Min Zhang, Shaoping Ma, Qingyao Ai


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. We have open-sourced all the code and data in https://github.com/LittleDinoC/StateDelta/.
Anthology ID:
2025.emnlp-main.518
Volume:
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10230–10251
Language:
URL:
https://aclanthology.org/2025.emnlp-main.518/
DOI:
Bibkey:
Cite (ACL):
Yichen Tang, Weihang Su, Yujia Zhou, Yiqun Liu, Min Zhang, Shaoping Ma, and Qingyao Ai. 2025. Augmenting Multi-Agent Communication with State Delta Trajectory. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 10230–10251, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Augmenting Multi-Agent Communication with State Delta Trajectory (Tang et al., EMNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.emnlp-main.518.pdf
Checklist:
 2025.emnlp-main.518.checklist.pdf