# Vision-Language Model Dialog Games for Self-Improvement

arXiv: https://arxiv.org/abs/2502.02740 · HTML: https://mlsanity.com/paper/2502.02740/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 4 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- Synthetic data and self-improvement for LLMs / [Self-improving MLLMs and synthetic data](https://mlsanity.com/synth/self-improving-mllms-and-synthetic-data/)

## Builds on (most cited first, 8 of 8)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains](https://mlsanity.com/paper/2501.05707/) (2025)
- [Synth2: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings](https://mlsanity.com/paper/2403.07750/) (2024)
- [Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency](https://mlsanity.com/paper/2310.03734/) (2023)
- [Using Game Play to Investigate Multimodal and Conversational Grounding in Large Multimodal Models](https://mlsanity.com/paper/2406.14035/) (2024)

## Built on by (most cited first, 4 of 4)

- [Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play](https://mlsanity.com/paper/2509.25541/) (2025)
- [Success and Cost Elicit Convention Formation for Efficient Communication](https://mlsanity.com/paper/2510.24023/) (2025)
- [Self-Improvement in Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2510.02665/) (2025)
- [Dynamic Adversarial Reinforcement Learning for Robust Multimodal Large Language Models](https://mlsanity.com/paper/2602.22227/) (2026)

## Abstract (arXiv)

The increasing demand for high-quality, diverse training data poses a significant bottleneck in advancing vision-language models (VLMs). This paper presents VLM Dialog Games, a novel and scalable self-improvement framework for VLMs. Our approach leverages self-play between two agents engaged in a goal-oriented play centered around image identification. By filtering for successful game interactions, we automatically curate a high-quality dataset of interleaved images and text. We demonstrate that fine-tuning on this synthetic data leads to performance gains on downstream tasks and generalises across datasets. Moreover, as the improvements in the model lead to better game play, this procedure can be applied iteratively. This work paves the way for self-improving VLMs, with potential applications in various real-world scenarios especially when the high-quality multimodal data is scarce.