arXiv:2501.07813v2 Announce Type: replace-cross
Abstract: Retrieval-augmented generation (RAG) agents are increasingly deployed to answer questions over local knowledge bases that cannot be centralized due to knowledge-sovereignty constraints. This results in two recurring failures in production: users do not know which agent to consult, and complex questions require evidence distributed across multiple agents. To overcome these challenges, we propose RIRS, a training-free orchestration framework to enable a multi-agent system for question answering. In detail, RIRS summarizes each agent’s local corpus in an embedding space, enabling a user-facing server to route queries only to the most relevant agents, reducing latency and avoiding noisy “broadcast-to-all” contexts. For complicated questions, the server can iteratively aggregate responses to derive intermediate results and refine the question to bridge the gap toward a comprehensive answer. Extensive experiments demonstrate the effectiveness of RIRS, including its ability to precisely select agents and provide accurate responses to single-hop queries, and its use of an iterative strategy to achieve accurate, multi-step resolutions for complex queries.
Dysregulation of Hippo Signaling Pathway as a Convergent Mechanism Underlying Choroid Plexus Defects in Bipolar Disorder
Bipolar disorder (BD) is a prevalent and highly heritable psychiatric condition. Developmental mechanisms are implicated but the specific molecular origins remain unclear. The choroid plexus