Metraipolis › archive › dc_2aadbb4bcb1f
Question-Specific Knowledge Graphs for Efficient Visual Reasoning — arXiv:2609.35942
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35942
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:56:23.192Z
- SHA-256 of the archived text
dd7dd7801356ca1f329c838466ce127f04230e0fd9be63733e3d1df52021afdc- Stable URL of this page
https://metraipolis.com/documento/dc_2aadbb4bcb1f
How to cite
Question-Specific Knowledge Graphs for Efficient Visual Reasoning — arXiv:2609.35942 — arXiv (en), https://arxiv.org/abs/2609.35942 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2aadbb4bcb1f (Metraipolis archive dc_2aadbb4bcb1f, sha256 dd7dd7801356ca1f329c838466ce127f04230e0fd9be63733e3d1df52021afdc)
BibTeX
@misc{dc2aadbb4bcb1f,
title = {Question-Specific Knowledge Graphs for Efficient Visual Reasoning — arXiv:2609.35942},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35942},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2aadbb4bcb1f; sha256 dd7dd7801356ca1f329c838466ce127f04230e0fd9be63733e3d1df52021afdc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35942. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent work in visual question answering has shown that vision-language models can exhibit strong reasoning capabilities by translating visual inputs into textual representations. The effectiveness of this translation depends on how well visual details are retained; models need to surface and align both explicit and implicit knowledge sufficient to support reasoning, without introducing spurious assumptions. Existing methods that leverage detailed image captions introduce visual details unrelated to the reasoning task, inflating input token counts and increasing computational cost. To address these challenges, we propose VisKG, a reinforcement learning (RL) framework in which models learn to translate visual content into question-specific knowledge graph (KG) representations. This process filters out perceptual noise while preserving the entity-relation structure needed for chain-of-thought reasoning, following the principle of minimum sufficient information. To ensure stable RL post-training, VisKG adopts Group reward-Decoupled Normalization Policy Optimization (GDPO). In addition, we strengthen the supervision stage with negative rationale samples, exposing the model to incorrect reasoning paths before RL post-training. Experimental results across science, mathematics, and general visual understanding benchmarks show that VisKG achieves performance comparable to or better than baselines, while requiring fewer tokens than caption-based representations. Moreover, training VisKG with GDPO improves accuracy by 2% over its GRPO-trained counterpart on average. These results suggest that KG representations are a promising approach for supporting multi-step reasoning and open up future work on adaptively selecting the most suitable representation for a given task. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.35942 — 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 2026-10-07T16:27:03.172Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).