# ManGo: Manga Active Narrative Grounding Optimization

arXiv: https://arxiv.org/abs/2608.29865 · HTML: https://mlsanity.com/paper/2608.29865/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe](https://mlsanity.com/paper/2509.18154/) (2025)
- [Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization](https://mlsanity.com/paper/2504.05812/) (2025)
- [ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration](https://mlsanity.com/paper/2411.16044/) (2024)
- [MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering](https://mlsanity.com/paper/2405.11985/) (2024)
- [Grounded Reinforcement Learning for Visual Reasoning](https://mlsanity.com/paper/2505.23678/) (2025)
- [Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning](https://mlsanity.com/paper/2508.09726/) (2025)
- [Kwai Keye-VL 1.5 Technical Report](https://mlsanity.com/paper/2509.01563/) (2025)
- [Building a Manga Dataset "Manga109" with Annotations for Multimedia Applications](https://mlsanity.com/paper/2005.04425/) (2020)
- [MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research](https://mlsanity.com/paper/2503.13399/) (2025)
- [How Far Can Unsupervised RLVR Scale LLM Training?](https://mlsanity.com/paper/2603.08660/) (2026)
- [EgoBlind: Towards Egocentric Visual Assistance for the Blind](https://mlsanity.com/paper/2503.08221/) (2025)
- [CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding](https://mlsanity.com/paper/2407.03550/) (2024)
- [Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual Questions](https://mlsanity.com/paper/2507.13773/) (2025)
- [MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding](https://mlsanity.com/paper/2505.20298/) (2025)
- [ComicsPAP: understanding comic strips by picking the correct panel](https://mlsanity.com/paper/2503.08561/) (2025)

## Abstract (arXiv)

Manga visual question answering requires models to answer questions over panel-based visual narratives, where relevant evidence is distributed across ordered panels, embedded text, recurring characters, and implicit event transitions. This structure makes passive page encoding insufficient, as the model must identify which panels to inspect, what clues to retain, and when the accumulated evidence is sufficient for answering. We propose ManGo (Manga Active Narrative Grounding Optimization), an unsupervised framework for active manga visual question answering. ManGo introduces Active Narrative Sketching (ANS), which iteratively selects panels, extracts concise grounded clues, and decides when to stop, forming a compact question-directed evidence sketch before answer generation. To optimize this behavior without human-annotated answers or rationale paths, ManGo samples multiple ANS rollouts and applies group-relative training with two rewards: answer preference from listwise self-ranking and path consistency from stable ordered panel trajectories. The combined reward is optimized with group-relative policy training, encouraging the model to improve both final answers and the panel-level evidence paths that support them. Experiments on standard manga understanding benchmarks show that ManGo achieves state-of-the-art performance across different settings.