# Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards

arXiv: https://arxiv.org/abs/2606.27376 · HTML: https://mlsanity.com/paper/2606.27376/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 48 references that are in the map.
- First posted on arXiv 25 Jun 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 18 of 18)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset](https://mlsanity.com/paper/2505.09568/) (2025)
- [SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation](https://mlsanity.com/paper/2404.14396/) (2024)
- [VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation](https://mlsanity.com/paper/2409.04429/) (2024)
- [X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again](https://mlsanity.com/paper/2507.22058/) (2025)
- [VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model](https://mlsanity.com/paper/2501.12327/) (2025)
- [LongCat-Next: Lexicalizing Modalities as Discrete Tokens](https://mlsanity.com/paper/2603.27538/) (2026)
- [EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards](https://mlsanity.com/paper/2511.16672/) (2025)
- [UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision](https://mlsanity.com/paper/2601.03193/) (2026)
- [UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning](https://mlsanity.com/paper/2505.23380/) (2025)
- [SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models](https://mlsanity.com/paper/2510.12784/) (2025)
- [VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning](https://mlsanity.com/paper/2504.02949/) (2025)
- [OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models](https://mlsanity.com/paper/2503.08686/) (2025)
- [SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards](https://mlsanity.com/paper/2506.07963/) (2025)
- [Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models](https://mlsanity.com/paper/2601.20305/) (2026)

## Built on by (most cited first, 7 of 7)

- [Dreaming in Flow: Generative Grounding Feedback for Self-Evolving Unified Multimodal Models](https://mlsanity.com/paper/2609.08282/) (2026)
- [Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots](https://mlsanity.com/paper/2608.09931/) (2026)
- [Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision](https://mlsanity.com/paper/2609.04203/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [Recursive Self-Improvement in Unified Multimodal Models](https://mlsanity.com/paper/2610.03002/) (2026)
- [Rubric-CEPR: Self-Evolving Image Editing via Reward-Verified Self-Distillation](https://mlsanity.com/paper/2610.12469/) (2026)
- [RSIgen: Reciprocal Self-Improvement for Agentic Visual Generation](https://mlsanity.com/paper/2610.18688/) (2026)

## Abstract (arXiv)

Most unified large multimodal models (LMMs) that support both visual understanding and image generation still rely on curated post-training supervision, such as human annotations, preference labels, or external reward models. We ask whether a unified LMM can improve both abilities autonomously using only unlabeled images. We propose a self-evolving training framework with three internal roles: a Proposer that generates visual questions, a Solver that answers and evaluates them, and a Generator that synthesizes images. Training uses only self-derived consistency signals, without human annotations, preference labels, or task-trained external reward/judge models. To stabilize learning, we introduce Solver Token Entropy (STE), a continuous difficulty signal based on token-level prediction uncertainty that remains useful even when sample-level consistency becomes unreliable. For image generation, we design a multi-scale internal evaluation scheme that combines question-answer fidelity scoring with cycle-consistent captioning. This creates a solver-mediated coupling, where better visual understanding enables more reliable generation assessment and stronger internal training signals. The framework preserves the same role decomposition, reward logic, and training schedule across diffusion-based BLIP3o, rectified-flow BAGEL, and autoregressive VARGPT-v1.1 architectures, requiring only each backbone's native prompting and generation interface. Across eight understanding metrics, our method consistently improves over the corresponding base models. On BAGEL, it achieves a +3.5% absolute gain on MMMU and improves GenEval image generation performance from 82% to 85%. Code and models are publicly released.