Words Instead of Weights? Self-Learning Multi-Agent RAG (HERA)
AI

Words Instead of Weights? Self-Learning Multi-Agent RAG (HERA)

By



Words Instead of Weights? Self-Learning Multi-Agent RAG (HERA)

The authors: ” … we propose HERA, a hierarchical framework that jointly evolves multi-agent orchestration and role-specific agent prompts. At the global level, HERA optimizes query-specific agent topologies through reward-guided sampling and experience accumulation.

At the local level, Role-Aware Prompt Evolution refines agent behaviors via credit assignment and dual-axes adaptation along operational and behavioral principles, enabling targeted, role-conditioned improvements. ”

All rights w/ authors:
“Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts”
Sha Li
Virginia Tech
Naren Ramakrishnan
Virginia Tech

#aiexplained
#chatgpt
#airesearch
#scienceeducation
#scienceexperiment