One Supervisor, Many Modalities: Adaptive Tool Orchestration for Autonomous Queries
This work addresses the challenge of efficient and cost-effective multimodal AI deployment for users handling complex queries across diverse data types, representing a novel method rather than an incremental improvement.
The paper tackles the problem of autonomous multimodal query processing by introducing an agentic AI framework with a central Supervisor that coordinates specialized tools across text, image, audio, video, and document modalities, resulting in a 72% reduction in time-to-accurate-answer, 85% reduction in conversational rework, and 67% cost reduction compared to a baseline while maintaining accuracy.
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.