Self-Evolving Visual Questioner

Hugging Face Daily Papers Papers
self-evolution visual-questioner vision-language-model question-generation self-supervision agentic-protocol

Summary

This paper introduces a self-evolving framework for vision-language models to improve their question-generation capabilities without external supervision, enhancing both question quality and answerer performance.

Vision-language models (VLMs) are typically trained as passive answerers, while their ability to actively ask diverse, non-trivial, visual-centric and grounded questions remains underexplored. Existing visual questioners' performance is bottlenecked by the availability of high-quality training data or the cost of curating them. We show that a VLM can continuously improve itself as a visual questioner without any external supervision. We propose a self-evolving framework that uses a VLM itself as both a proposer and a filter to produce harder, more informative, and visual-centric questions, while maintaining their exploration diversity to avoid training collapse. These questions are then used to train the VLM in both questioner and answerer modes. To evaluate the questioner, we introduce an agentic protocol that assesses questions along perception, reasoning, and diversity dimensions. Experiments across various backbone VLMs show that our method substantially enhances the quality and substantially expands the difficulty boundary of autonomous question generation. Under the same budget, our self-supervision is more effective than training on the static source data. Moreover, the self-evolving questioner remains a competitive or even better answerer.
Original Article
View Cached Full Text

Cached at: 06/17/26, 07:52 PM

Paper page - Self-Evolving Visual Questioner

Source: https://huggingface.co/papers/2606.13929

Abstract

A vision-language model autonomously improves its question-generation capabilities through self-evolution, enhancing both question quality and answerer performance without external supervision.

Vision-language models(VLMs) are typically trained as passive answerers, while their ability to actively ask diverse, non-trivial, visual-centric and grounded questions remains underexplored. Existingvisual questioners’ performance is bottlenecked by the availability of high-qualitytraining dataor the cost of curating them. We show that a VLM can continuously improve itself as avisual questionerwithout any external supervision. We propose aself-evolving frameworkthat uses a VLM itself as both a proposer and a filter to produce harder, more informative, andvisual-centric questions, while maintaining their exploration diversity to avoidtraining collapse. These questions are then used to train the VLM in both questioner andanswerer modes. To evaluate the questioner, we introduce anagentic protocolthat assesses questions along perception, reasoning, and diversity dimensions. Experiments across various backbone VLMs show that our method substantially enhances the quality and substantially expands the difficulty boundary of autonomousquestion generation. Under the same budget, our self-supervision is more effective than training on the static source data. Moreover, the self-evolving questioner remains a competitive or even better answerer.

View arXiv pageView PDFProject pageGitHub0Add to collection

Get this paper in your agent:

hf papers read 2606\.13929

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.13929 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.13929 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.13929 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory

Hugging Face Daily Papers

SuperMemory-VQA is a new egocentric VQA benchmark featuring 52.9 hours of AI-glasses footage and 4,853 QA pairs designed to evaluate AI assistants on long-horizon memory tasks spanning object recall, intent, timelines, and conversations. Benchmarking reveals existing agentic frameworks and LLMs remain far from reliable on these real-world memory challenges.