Latent Collaboration in Multi-Agent Systems

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zou, Jiaru, Qiu, Ruizhong, Li, Gaotang, Yang, Xiyuan, Tieu, Katherine, Lu, Pan, Shen, Ke, Tong, Hanghang, Choi, Yejin, He, Jingrui, Zou, James, Wang, Mengdi, Yang, Ling
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917551625207808
author Zou, Jiaru
Qiu, Ruizhong
Li, Gaotang
Yang, Xiyuan
Tieu, Katherine
Lu, Pan
Shen, Ke
Tong, Hanghang
Choi, Yejin
He, Jingrui
Zou, James
Wang, Mengdi
Yang, Ling
author_facet Zou, Jiaru
Qiu, Ruizhong
Li, Gaotang
Yang, Xiyuan
Tieu, Katherine
Lu, Pan
Shen, Ke
Tong, Hanghang
Choi, Yejin
He, Jingrui
Zou, James
Wang, Mengdi
Yang, Ling
contents Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we take a step forward by enabling models to collaborate directly within the continuous latent space. We introduce LatentMAS, an end-to-end training-free framework that enables pure latent collaboration among LLM agents. In LatentMAS, each agent first performs auto-regressive latent thoughts generation through last-layer hidden embeddings instead of text. Then, a shared latent working memory preserves and transfers each agent's internal representations and latent thoughts, ensuring lossless information exchange without re-encoding. We provide detailed theoretical analyses showing that LatentMAS achieves higher expressiveness and lossless information preservation with lower overall complexity than standard text-based MAS. In addition, empirical evaluations across 9 comprehensive benchmarks spanning math and science reasoning, commonsense understanding, and code generation show that LatentMAS outperforms advanced single agents and text-based MAS baselines, achieving up to 14.6% higher accuracy, reducing output token usage by 70.8%-83.7%, and providing 4$\times$-4.3$\times$ faster end-to-end inference. Code and data are fully open-sourced at https://github.com/Gen-Verse/LatentMAS.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20639
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Latent Collaboration in Multi-Agent Systems
Zou, Jiaru
Qiu, Ruizhong
Li, Gaotang
Yang, Xiyuan
Tieu, Katherine
Lu, Pan
Shen, Ke
Tong, Hanghang
Choi, Yejin
He, Jingrui
Zou, James
Wang, Mengdi
Yang, Ling
Computation and Language
Artificial Intelligence
Machine Learning
Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we take a step forward by enabling models to collaborate directly within the continuous latent space. We introduce LatentMAS, an end-to-end training-free framework that enables pure latent collaboration among LLM agents. In LatentMAS, each agent first performs auto-regressive latent thoughts generation through last-layer hidden embeddings instead of text. Then, a shared latent working memory preserves and transfers each agent's internal representations and latent thoughts, ensuring lossless information exchange without re-encoding. We provide detailed theoretical analyses showing that LatentMAS achieves higher expressiveness and lossless information preservation with lower overall complexity than standard text-based MAS. In addition, empirical evaluations across 9 comprehensive benchmarks spanning math and science reasoning, commonsense understanding, and code generation show that LatentMAS outperforms advanced single agents and text-based MAS baselines, achieving up to 14.6% higher accuracy, reducing output token usage by 70.8%-83.7%, and providing 4$\times$-4.3$\times$ faster end-to-end inference. Code and data are fully open-sourced at https://github.com/Gen-Verse/LatentMAS.
title Latent Collaboration in Multi-Agent Systems
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2511.20639