AIDE: Agentically Improve Visual Language Model with Domain Experts
This work addresses the problem of improving VLMs for researchers and developers working with limited access to large models or human supervision.
The authors tackled the problem of improving Visual Language Models (VLMs) without relying on larger models, and achieved notable performance gains through their AIDE framework. Experiments on multiple benchmarks demonstrated the effectiveness of AIDE in enhancing VLM capabilities.
The enhancement of Visual Language Models (VLMs) has traditionally relied on knowledge distillation from larger, more capable models. This dependence creates a fundamental bottleneck for improving state-of-the-art systems, particularly when no superior models exist. We introduce AIDE (Agentic Improvement through Domain Experts), a novel framework that enables VLMs to autonomously enhance their capabilities by leveraging specialized domain expert models. AIDE operates through a four-stage process: (1) identifying instances for refinement, (2) engaging domain experts for targeted analysis, (3) synthesizing expert outputs with existing data, and (4) integrating enhanced instances into the training pipeline. Experiments on multiple benchmarks, including MMMU, MME, MMBench, etc., demonstrate AIDE's ability to achieve notable performance gains without relying on larger VLMs nor human supervision. Our framework provides a scalable, resource-efficient approach to continuous VLM improvement, addressing critical limitations in current methodologies, particularly valuable when larger models are unavailable to access.