Metraipolis › archive › dc_bf87fb2f20e5

From Scene Graphs to Answers: Selective Neuro-Symbolic Reasoning for Autonomous Driving — arXiv:2609.32645

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32645
License (as archived)
CC0-1.0
Archived
2026-10-07T20:55:51.216Z
SHA-256 of the archived text
d3e78e49fcc69e61f78ced9e5d97ee9559222cd8f67d6ffb90edb60eb4696771
Stable URL of this page
https://metraipolis.com/documento/dc_bf87fb2f20e5

How to cite

From Scene Graphs to Answers: Selective Neuro-Symbolic Reasoning for Autonomous Driving — arXiv:2609.32645 — arXiv (en), https://arxiv.org/abs/2609.32645 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf87fb2f20e5 (Metraipolis archive dc_bf87fb2f20e5, sha256 d3e78e49fcc69e61f78ced9e5d97ee9559222cd8f67d6ffb90edb60eb4696771)
BibTeX
@misc{dcbf87fb2f20e5,
  title = {From Scene Graphs to Answers: Selective Neuro-Symbolic Reasoning for Autonomous Driving — arXiv:2609.32645},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32645},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf87fb2f20e5; sha256 d3e78e49fcc69e61f78ced9e5d97ee9559222cd8f67d6ffb90edb60eb4696771},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32645. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous-driving question answering requires reasoning over structured scene information, yet existing vision-language approaches largely delegate heterogeneous reasoning operations to a single neural inference process. We argue that this uniform strategy overlooks a fundamental distinction: some queries admit exact symbolic solutions, while others require semantic interpretation. We introduce a query-adaptive neuro-symbolic reasoning framework that explicitly allocates computation according to the nature of the query. At its core is a hierarchical Spatiotemporal Scene Graph (STSG) that separates persistent object identities from frame-specific states and represents spatial relations and temporal transitions as explicit directed structures. Given a query, a symbolic executor first attempts to resolve it through exact graph operations; only when symbolic execution abstains is an LLM invoked for semantic reasoning. For these unresolved queries, query-conditioned graph retrieval and evidence filtering preserve relation direction, temporal locality, and object semantics, providing the LLM with compact and verified task-relevant evidence. This design shifts the role of the LLM from a universal reasoning engine to a targeted semantic reasoner, while allowing deterministic computation to be handled exactly and efficiently. We evaluate the framework on 5,916 NuScenes-QA questions across all ten scenes of nuScenes v1.0-mini under an oracle-perception setting. The complete system achieves 80.63 percent overall accuracy with GPT-5.4-mini, improving over the corresponding LLM-only configuration by 5.48 percentage points; with DeepSeek-V4-Flash, the improvement reaches 6.64 points. The largest gains occur on counting questions, with improvements of 10.20 and 12.61 points, respectively. These results show that selective reasoning improves both accuracy and inference efficiency.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.32645 — 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 2026-10-07T20:29:00.900Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).