Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zaremehrjerdi, Hossein, Ganguly, Shreyan, Rairdin, Ashlyn, Tranel, Elizabeth, Feuer, Benjamin, Di Salvo, Juan Ignacio, Panthulugiri, Srikanth, Pacin, Hernan Torres, Moser, Victoria, Jones, Sarah, Raigne, Joscif G, Shen, Yanben, Dornath, Heidi M., Balu, Aditya, Krishnamurthy, Adarsh, Singh, Asheesh K, Singh, Arti, Ganapathysubramanian, Baskar, Hegde, Chinmay, Sarkar, Soumik
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.19259
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915308267110400
author Zaremehrjerdi, Hossein
Ganguly, Shreyan
Rairdin, Ashlyn
Tranel, Elizabeth
Feuer, Benjamin
Di Salvo, Juan Ignacio
Panthulugiri, Srikanth
Pacin, Hernan Torres
Moser, Victoria
Jones, Sarah
Raigne, Joscif G
Shen, Yanben
Dornath, Heidi M.
Balu, Aditya
Krishnamurthy, Adarsh
Singh, Asheesh K
Singh, Arti
Ganapathysubramanian, Baskar
Hegde, Chinmay
Sarkar, Soumik
author_facet Zaremehrjerdi, Hossein
Ganguly, Shreyan
Rairdin, Ashlyn
Tranel, Elizabeth
Feuer, Benjamin
Di Salvo, Juan Ignacio
Panthulugiri, Srikanth
Pacin, Hernan Torres
Moser, Victoria
Jones, Sarah
Raigne, Joscif G
Shen, Yanben
Dornath, Heidi M.
Balu, Aditya
Krishnamurthy, Adarsh
Singh, Asheesh K
Singh, Arti
Ganapathysubramanian, Baskar
Hegde, Chinmay
Sarkar, Soumik
contents Agricultural decision-making involves complex, context-specific reasoning, where choices about crops, practices, and interventions depend heavily on geographic, climatic, and economic conditions. Traditional large language models (LLMs) often fall short in navigating this nuanced problem due to limited reasoning capacity. We hypothesize that recent advances in large reasoning models (LRMs) can better handle such structured, domain-specific inference. To investigate this, we introduce AgReason, the first expert-curated open-ended science benchmark with 100 questions for agricultural reasoning. Evaluations across thirteen open-source and proprietary models reveal that LRMs outperform conventional ones, though notable challenges persist, with the strongest Gemini-based baseline achieving 36% accuracy. We also present AgThoughts, a large-scale dataset of 44.6K question-answer pairs generated with human oversight and equipped with synthetically generated reasoning traces. Using AgThoughts, we develop AgThinker, a suite of small reasoning models that can be run on consumer-grade GPUs, and show that our dataset can be effective in unlocking agricultural reasoning abilities in LLMs. Our project page is here: https://baskargroup.github.io/Ag_reasoning/
format Preprint
id arxiv_https___arxiv_org_abs_2505_19259
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Large Reasoning Models for Agriculture
Zaremehrjerdi, Hossein
Ganguly, Shreyan
Rairdin, Ashlyn
Tranel, Elizabeth
Feuer, Benjamin
Di Salvo, Juan Ignacio
Panthulugiri, Srikanth
Pacin, Hernan Torres
Moser, Victoria
Jones, Sarah
Raigne, Joscif G
Shen, Yanben
Dornath, Heidi M.
Balu, Aditya
Krishnamurthy, Adarsh
Singh, Asheesh K
Singh, Arti
Ganapathysubramanian, Baskar
Hegde, Chinmay
Sarkar, Soumik
Machine Learning
Artificial Intelligence
Agricultural decision-making involves complex, context-specific reasoning, where choices about crops, practices, and interventions depend heavily on geographic, climatic, and economic conditions. Traditional large language models (LLMs) often fall short in navigating this nuanced problem due to limited reasoning capacity. We hypothesize that recent advances in large reasoning models (LRMs) can better handle such structured, domain-specific inference. To investigate this, we introduce AgReason, the first expert-curated open-ended science benchmark with 100 questions for agricultural reasoning. Evaluations across thirteen open-source and proprietary models reveal that LRMs outperform conventional ones, though notable challenges persist, with the strongest Gemini-based baseline achieving 36% accuracy. We also present AgThoughts, a large-scale dataset of 44.6K question-answer pairs generated with human oversight and equipped with synthetically generated reasoning traces. Using AgThoughts, we develop AgThinker, a suite of small reasoning models that can be run on consumer-grade GPUs, and show that our dataset can be effective in unlocking agricultural reasoning abilities in LLMs. Our project page is here: https://baskargroup.github.io/Ag_reasoning/
title Towards Large Reasoning Models for Agriculture
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.19259