Metraipolis › archive › dc_82964bbc0692

How Well Do LLMs Reason with Noisy Evidence? An Active Visual Reasoning Benchmark — arXiv:2610.07751

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07751
License (as archived)
CC0-1.0
Archived
2026-10-07T11:19:03.750Z
SHA-256 of the archived text
72b056521751a50e10e3b62a7a99ca155cb17650f31c657e9694d464a9c14407
Stable URL of this page
https://metraipolis.com/documento/dc_82964bbc0692

How to cite

How Well Do LLMs Reason with Noisy Evidence? An Active Visual Reasoning Benchmark — arXiv:2610.07751 — arXiv (en), https://arxiv.org/abs/2610.07751 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_82964bbc0692 (Metraipolis archive dc_82964bbc0692, sha256 72b056521751a50e10e3b62a7a99ca155cb17650f31c657e9694d464a9c14407)
BibTeX
@misc{dc82964bbc0692,
  title = {How Well Do LLMs Reason with Noisy Evidence? An Active Visual Reasoning Benchmark — arXiv:2610.07751},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07751},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_82964bbc0692; sha256 72b056521751a50e10e3b62a7a99ca155cb17650f31c657e9694d464a9c14407},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07751. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-world reasoning rarely reduces to static question answering: agents must actively gather information from tools and sensors that are often noisy and unreliable. Yet most existing active reasoning benchmarks assume that environmental feedback is trustworthy, or introduce noise without exposing an explicit, calibrated uncertainty signal, leaving open how LLMs should reason when the evidence itself is uncertain. We introduce VisualNoiseQA, a novel benchmark for active reasoning under noisy visual feedback. A text-only LLM must solve VQA problems by iteratively querying a fixed, off-the-shelf VLM treated as a stochastic visual sensor. For each query, we draw multiple samples and expose an empirical uncertainty signal via self-consistency, enabling the reasoner to probe from different angles and decide what to ask next and when to stop. Our construction is automatic and scalable: starting from diverse VQA sources and two noisy VLMs, we retain only questions where the sensor is inconsistent yet human-solvable. We evaluate multiple LLM reasoners on 1,000 instances spanning perception, chart understanding, and knowledge-intensive reasoning. VisualNoiseQA thus provides a controlled playground to study how different LLMs exploit uncertainty signals for robust reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.07751 — 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 2026-10-07T11:15:24.548Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).