AIDE: Agentically Improve Visual Language Model with Domain Experts

ACL ARR 2025 February Submission939 Authors

Abstract: 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 AIDEs ability to achieve notable performance gains without relying on larger VLMs. 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 or impractical to access.

Paper Type: Short

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Research Area Keywords: Expert, MLLM, Multimodal

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Position papers

Languages Studied: English

Submission Number: 939