<ul><li>Agentic Neural Network(ANN) is a framework that conceptualizes multi-agent collaboration as a layered neural network architecture.</li><li>ANN follows a two-phase optimization strategy: Forward Phase dynamically decomposes tasks into subtasks, while the Backward Phase refines collaboration through iterative feedback.</li><li>This neuro-symbolic approach enables ANN to create new or specialized agent teams post-training, leading to gains in accuracy and adaptability.</li><li>Across four benchmark datasets, ANN outperforms leading multi-agent baselines, demonstrating improved performance and scalability.</li></ul>

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

Discover more