One Supervisor, Many Modalities: Adaptive Tool Orchestration for Autonomous Queries

TL;DR

This paper introduces an adaptive AI framework that dynamically orchestrates multiple modalities and tools for autonomous query processing, significantly improving efficiency and reducing costs while maintaining accuracy.

Contribution

It presents a novel agentic AI system with a central Supervisor that coordinates multimodal tools using adaptive routing strategies, enhancing autonomous query handling.

Findings

72% reduction in time-to-accurate-answer

85% reduction in conversational rework

67% cost reduction

Abstract

We present an agentic AI framework for autonomous multimodal query processing that coordinates specialized tools across text, image, audio, video, and document modalities. A central Supervisor dynamically decomposes user queries, delegates subtasks to modality-appropriate tools (e.g., object detection, OCR, speech transcription), and synthesizes results through adaptive routing strategies rather than predetermined decision trees. For text-only queries, the framework uses learned routing via RouteLLM, while non-text paths use SLM-assisted modality decomposition. Evaluated on 2,847 queries across 15 task categories, our framework achieves 72% reduction in time-to-accurate-answer, 85% reduction in conversational rework, and 67% cost reduction compared to the matched hierarchical baseline while maintaining accuracy parity. These results demonstrate that intelligent centralized orchestration fundamentally improves multimodal AI deployment economics.