Differentiable Mixture-of-Agents Incentivizes Swarm Intelligence of Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wu, Xingjian, Lu, Junkai, Yan, Siyu, Qiu, Xiangfei, Hu, Jilin, Guo, Chenjuan, Yang, Bin
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914617375064064
author Wu, Xingjian
Lu, Junkai
Yan, Siyu
Qiu, Xiangfei
Hu, Jilin
Guo, Chenjuan
Yang, Bin
author_facet Wu, Xingjian
Lu, Junkai
Yan, Siyu
Qiu, Xiangfei
Hu, Jilin
Guo, Chenjuan
Yang, Bin
contents Recent advances in Large Language Models (LLMs) have catalyzed the development of multi-agent systems (MAS) for complex reasoning tasks. However, existing MAS typically rely on pre-defined or pre-compiled communication topologies, which limits their flexibility and adaptability to dynamic task requirements. In this work, we propose Differentiable Mixture-of-Agents (DMoA), a self-evolving multi-agent framework that enables elastic and adaptive agent collaboration during inference. Instead of statically constructing workflows, DMoA dynamically routes and activates agents at each reasoning step, allowing the system to implicitly simulate diverse communication topologies and adapt to evolving demands. To achieve this, we design a differentiable, context-aware routing mechanism that leverages recurrent structures to incorporate historical and contextual information, producing sparse agent activations in a step-wise manner. Furthermore, we introduce predictive entropy as self-supervised signals to optimize the routing process, enabling efficient test-time adaptation without external annotations. Extensive experiments across 9 benchmarks demonstrate that DMoA achieves state-of-the-art performance while exhibiting strong efficiency, robustness, and ensembling capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15706
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Differentiable Mixture-of-Agents Incentivizes Swarm Intelligence of Large Language Models
Wu, Xingjian
Lu, Junkai
Yan, Siyu
Qiu, Xiangfei
Hu, Jilin
Guo, Chenjuan
Yang, Bin
Machine Learning
Recent advances in Large Language Models (LLMs) have catalyzed the development of multi-agent systems (MAS) for complex reasoning tasks. However, existing MAS typically rely on pre-defined or pre-compiled communication topologies, which limits their flexibility and adaptability to dynamic task requirements. In this work, we propose Differentiable Mixture-of-Agents (DMoA), a self-evolving multi-agent framework that enables elastic and adaptive agent collaboration during inference. Instead of statically constructing workflows, DMoA dynamically routes and activates agents at each reasoning step, allowing the system to implicitly simulate diverse communication topologies and adapt to evolving demands. To achieve this, we design a differentiable, context-aware routing mechanism that leverages recurrent structures to incorporate historical and contextual information, producing sparse agent activations in a step-wise manner. Furthermore, we introduce predictive entropy as self-supervised signals to optimize the routing process, enabling efficient test-time adaptation without external annotations. Extensive experiments across 9 benchmarks demonstrate that DMoA achieves state-of-the-art performance while exhibiting strong efficiency, robustness, and ensembling capabilities.
title Differentiable Mixture-of-Agents Incentivizes Swarm Intelligence of Large Language Models
topic Machine Learning
url https://arxiv.org/abs/2605.15706