Metraipolis › archive › dc_88ddb47243e7
ManGo: Manga Active Narrative Grounding Optimization — arXiv:2608.29865
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29865
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:07:12.662Z
- SHA-256 of the archived text
116cf0d374b0fca87dab5efc3dad7c7988a24c013657ef697176da80caf1ed0d- Stable URL of this page
https://metraipolis.com/documento/dc_88ddb47243e7
How to cite
ManGo: Manga Active Narrative Grounding Optimization — arXiv:2608.29865 — arXiv (en), https://arxiv.org/abs/2608.29865 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_88ddb47243e7 (Metraipolis archive dc_88ddb47243e7, sha256 116cf0d374b0fca87dab5efc3dad7c7988a24c013657ef697176da80caf1ed0d)
BibTeX
@misc{dc88ddb47243e7,
title = {ManGo: Manga Active Narrative Grounding Optimization — arXiv:2608.29865},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29865},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_88ddb47243e7; sha256 116cf0d374b0fca87dab5efc3dad7c7988a24c013657ef697176da80caf1ed0d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29865. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.29865 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:47:52.745Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).