---
title: "Integrating Domain Adaptation and Retrieval-Augmented Generation for Saline-Alkali Land Reclamation Planning"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.02883v1"
permalink: "https://feed.astralor.com/items/itm_939ebba1502601ce0859e9c4"
published: "2026-11-02T10:19:14.000Z"
score: 58
channel: "tech"
tags: ["OpenAI","RAG","多模态","Integrating Domain Adaptation","Retrieval-Augmented Generation","Saline-Alkali Land Reclamation","Planning Reclamation","Wenyao"]
---

# Integrating Domain Adaptation and Retrieval-Augmented Generation for Saline-Alkali Land Reclamation Planning

## 速览

Reclamation of saline-alkali land requires management plans that account for soil and water conditions, treatment evidence, and financial constraints. This study develops Wenyao, an agricultural decision-support system …

## 关键点

- Reclamation of saline-alkali land requires management plans that account for soil and water conditions, treatment evidence, and financial constraints.
- This study develops Wenyao, an agricultural decision-support system integrating domain adaptation with retrieval-augmented generation.
- A bilingual corpus of 8,664 research papers was processed using a 110-indicator schema to construct SA-Bench, comprising 4,860 paper-level planning instances.

## 全文

Reclamation of saline-alkali land requires management plans that account for soil and water conditions, treatment evidence, and financial constraints. This study develops Wenyao, an agricultural decision-support system integrating domain adaptation with retrieval-augmented generation. A bilingual corpus of 8,664 research papers was processed using a 110-indicator schema to construct SA-Bench, comprising 4,860 paper-level planning instances. A QwQ-32B model was adapted through low-rank supervised fine-tuning and combined with case retrieval for budget-conditioned planning. Evidence extraction achieved an F1-score of 0.83 on 300 expert-annotated papers. Without retrieval, Wenyao achieved 95.83% accuracy on 936 source-disjoint multiple-choice questions, compared with 87.93% for the strongest general-purpose baseline; removing explanatory supervision reduced accuracy to 89.42%. Matched-evidence comparisons across 69 region-budget cases supported complementary contributions from adaptation and retrieval. In a blind assessment by 31 experts, Wenyao with retrieval obtained the highest mean scores for objectives and projected outcomes, whereas GPT-5 scored highest for cost estimates. These findings support literature-informed reclamation planning with professional review, while ongoing field monitoring will assess soil and crop responses.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_939ebba1502601ce0859e9c4