Cost-Aware Tool-Routing Agents for Verifiable Agricultural Decision Support: An Offline Replay Benchmark
Stout in Computer Science and Technology Studies · 25.01.2026 · 2 (1) · 147-158
DOI: 10.61424/d5mjap37 ↗Kurz gefasst
Fachartikel in der Zeitschrift Stout in Computer Science and Technology Studies, online erschienen am 25.01.2026. Verfasst von Kevin Zhang und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Agricultural assistants must choose data and analytical tools without confusing source coverage, prediction, and verified evidence. We evaluated a constrained routing workflow using South Asian soil grids, Ethiopian cereal statistics, World Development Indicators, a flood archive, and the ND-GAIN composite index. The benchmark comprised 550 held-out requests: 420 supported queries, 70 unavailable-record probes, and 60 out-of-scope requests. Fixed execution, keyword rules, a supervised TF–IDF router, a selective variant, and a 77-million-parameter FLAN-T5-small router were compared under four operation budgets. At budget four, rules completed all supported tasks, TF–IDF completed 95.0%, and constrained FLAN-T5-small completed 38.6%. Rules used 1.15 source calls per request, compared with six for unrestricted fixed execution. Schema and identity checks rejected all 420 real-record substitution challenges, while removing verification produced incorrect accepted responses. A separate 284-observation forecasting test found that persistence achieved the lowest mean absolute error, 322.51 kg/ha. These results locate the main benefit in explicit evidence scope and efficient execution; they do not establish a general advantage for language-model routing. The evaluation concerns templated offline requests with resolved arguments, rather than autonomous field decisions.
Zitieren
APA
Zhang, K., Chen, Y., & Wu, D. (2026). Cost-Aware Tool-Routing Agents for Verifiable Agricultural Decision Support: An Offline Replay Benchmark. Stout in Computer Science and Technology Studies, 2(1), 147-158. https://doi.org/10.61424/d5mjap37
Vancouver
Zhang K, Chen Y, Wu D. Cost-Aware Tool-Routing Agents for Verifiable Agricultural Decision Support: An Offline Replay Benchmark. Stout in Computer Science and Technology Studies. 2026;2(1):147-158. doi:10.61424/d5mjap37
BibTeX
@article{Zhang2026,
author = {Zhang, Kevin and Chen, Yuxin and Wu, Daniel},
title = {Cost-Aware Tool-Routing Agents for Verifiable Agricultural Decision Support: An Offline Replay Benchmark},
journal = {Stout in Computer Science and Technology Studies},
year = {2026},
volume = {2},
number = {1},
pages = {147--158},
doi = {10.61424/d5mjap37}
}
EUVIMED