Reflective Dialogue between Teacher and Solver Agents for Video Question Answering
For researchers in video understanding, this work offers an inference-time adaptation technique that outperforms zero-shot and standard in-context learning, though it is a specific solution for a benchmark challenge.
The paper proposes a Reflective Dialogue method for Video Question Answering that adapts Vision-Language Models at inference time using only a small labeled support set, without fine-tuning. The method achieves 3rd place in the Open-source Track of the EgoCross Challenge at CVPR 2026.
Various approaches have been proposed to adapt Vision-Language Models (VLMs) to specialized domains for Video Question Answering, including fine-tuning and in-context learning. However, acquiring task-specific knowledge at the inference phase from only a small labeled support set without fine-tuning remains a challenge. In this paper, we propose a method that achieves adaptation solely through inference-time context injection. Our method first constructs a Reflective Dialogue (RD) -- a multi-turn conversation between two agents, in which Teacher poses each support question and delivers correctness feedback, and Solver answers and provides visual grounding explanations (or reflections) for both correct and incorrect answers. This dialogue history is then used as context at the inference phase. Experiments on the EgoCross benchmark demonstrate that our method outperforms both a baseline zero-shot setting and a standard in-context learning approach that passes support set examples directly, achieving 3rd place in the Open-source Track of the 1st Cross-Domain EgoCross Challenge at the CVPR 2026 EgoVis Workshop, for which this paper also serves as a technical report.