Metraipolis › archive › dc_25d567177aba
ATLAS-Bench: An Agentic Tool-Use Benchmark for Local Area Search — arXiv:2610.39438
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39438
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:09:18.282Z
- SHA-256 of the archived text
272536e58e7e5a29db78d050fa3a2998471d620d958c6ee74240965e3790679c- Stable URL of this page
https://metraipolis.com/documento/dc_25d567177aba
How to cite
ATLAS-Bench: An Agentic Tool-Use Benchmark for Local Area Search — arXiv:2610.39438 — arXiv (en), https://arxiv.org/abs/2610.39438 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_25d567177aba (Metraipolis archive dc_25d567177aba, sha256 272536e58e7e5a29db78d050fa3a2998471d620d958c6ee74240965e3790679c)
BibTeX
@misc{dc25d567177aba,
title = {ATLAS-Bench: An Agentic Tool-Use Benchmark for Local Area Search — arXiv:2610.39438},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39438},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_25d567177aba; sha256 272536e58e7e5a29db78d050fa3a2998471d620d958c6ee74240965e3790679c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39438. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reliable local search is essential for LLM agents to support everyday decisions and longer plans by finding places that meet users' needs at given times and locations. Yet existing benchmarks provide limited coverage of whether search results satisfy mandatory requirements, account for preferences, and ground factual and experiential judgments in place attributes and reviews. We introduce ATLAS-Bench, a benchmark of 1,200 queries across three regions, expanded from real search events using place attributes, reviews, and existing user profiles from the platform. Each query distinguishes mandatory requirements from preferences and factual conditions from subjective judgments, with supporting evidence and criteria for checking each requirement. Queries are validated through iterative assertion checks and cross-model review. We also introduce ATLASBox, a standardized evaluation environment with search tools and a fixed point-of-interest (POI) knowledge base. Given a query, timestamp, and location, an agent searches place attributes and reviews to recommend evidence-supported options or report that no place meets all mandatory requirements. We evaluate answer quality, trajectory quality, and execution cost. Across 14 configurations of 11 models, GPT-6-Luna achieves the highest constraint satisfaction rate among returned recommendations (71.5%) and factual accuracy (95.6%). However, it returns at least one acceptable recommendation for fewer satisfiable queries than GLM-5.3 (67.3% versus 85.3%). These results highlight the challenge of satisfying individual requirements while providing usable recommendations across queries. 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/2610.39438 — 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 2026-10-31T06:07:08.521Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).