Agentic Neural Networks: Self-Evolving Multi-Agent Systems via Textual Backpropagation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ma, Xiaowen, Lin, Chenyang, Zhang, Yao, Tresp, Volker, Ma, Yunpu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916849568972800
author Ma, Xiaowen
Lin, Chenyang
Zhang, Yao
Tresp, Volker
Ma, Yunpu
author_facet Ma, Xiaowen
Lin, Chenyang
Zhang, Yao
Tresp, Volker
Ma, Yunpu
contents Leveraging multiple Large Language Models(LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcome these constraints, we present the Agentic Neural Network(ANN), a framework that conceptualizes multi-agent collaboration as a layered neural network architecture. In this design, each agent operates as a node, and each layer forms a cooperative "team" focused on a specific subtask. Agentic Neural Network follows a two-phase optimization strategy: (1) Forward Phase-Drawing inspiration from neural network forward passes, tasks are dynamically decomposed into subtasks, and cooperative agent teams with suitable aggregation methods are constructed layer by layer. (2) Backward Phase-Mirroring backpropagation, we refine both global and local collaboration through iterative feedback, allowing agents to self-evolve their roles, prompts, and coordination. This neuro-symbolic approach enables ANN to create new or specialized agent teams post-training, delivering notable gains in accuracy and adaptability. Across four benchmark datasets, ANN surpasses leading multi-agent baselines under the same configurations, showing consistent performance improvements. Our findings indicate that ANN provides a scalable, data-driven framework for multi-agent systems, combining the collaborative capabilities of LLMs with the efficiency and flexibility of neural network principles. We plan to open-source the entire framework.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09046
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Agentic Neural Networks: Self-Evolving Multi-Agent Systems via Textual Backpropagation
Ma, Xiaowen
Lin, Chenyang
Zhang, Yao
Tresp, Volker
Ma, Yunpu
Machine Learning
Artificial Intelligence
Multiagent Systems
Leveraging multiple Large Language Models(LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcome these constraints, we present the Agentic Neural Network(ANN), a framework that conceptualizes multi-agent collaboration as a layered neural network architecture. In this design, each agent operates as a node, and each layer forms a cooperative "team" focused on a specific subtask. Agentic Neural Network follows a two-phase optimization strategy: (1) Forward Phase-Drawing inspiration from neural network forward passes, tasks are dynamically decomposed into subtasks, and cooperative agent teams with suitable aggregation methods are constructed layer by layer. (2) Backward Phase-Mirroring backpropagation, we refine both global and local collaboration through iterative feedback, allowing agents to self-evolve their roles, prompts, and coordination. This neuro-symbolic approach enables ANN to create new or specialized agent teams post-training, delivering notable gains in accuracy and adaptability. Across four benchmark datasets, ANN surpasses leading multi-agent baselines under the same configurations, showing consistent performance improvements. Our findings indicate that ANN provides a scalable, data-driven framework for multi-agent systems, combining the collaborative capabilities of LLMs with the efficiency and flexibility of neural network principles. We plan to open-source the entire framework.
title Agentic Neural Networks: Self-Evolving Multi-Agent Systems via Textual Backpropagation
topic Machine Learning
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2506.09046