arXiv cs.AI· Federico Mazzoni, Andrea Failla·· 6 天前AI 评分24
iRAG：面向人在回路决策支持的增量式检索增强生成系统
Incremental Retrieval-Augmented Generation for Human-in-the-Loop Decision Support
AI 导读
研究者提出 iRAG，将 RAG 与混合决策结合，针对知识库初始为空、靠人类决策逐步填充的场景，把过往决策存为可检索先例，并从静默观察演进到有证据支撑的质疑，最终实现带弃权的自主处理。
正文 · 原文
Abstract:We introduce iRAG, a human-in-the-loop decision-support system combining Retrieval-Augmented Generation (RAG) with Hybrid Decision-Making. Unlike conventional RAG systems, relying on static Knowledge Bases (KBs), our proposal addresses settings where the KB is initially empty and is progressively populated through human decisions. The system stores previous decisions as retrievable precedents and moves from silent observation to evidence-grounded contestation and, finally, to autonomous handling with abstention. Against an independent baseline, iRAG matches final-decision error under 10% drift without retrieval decay and reduces it under 40% drift across all configurations. Retrieval decay improves performance on changed knowledge while increasing error on stable knowledge, evidencing a stability--plasticity trade-off rather than a general advantage. Human oversight is an architectural provision of the workflow; its usability with real human users remains to be evaluated.
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.12666 [cs.HC] |
| (or arXiv:2610.12666v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12666 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Federico Mazzoni [view email]
[v1]
Thu, 8 Oct 2026 19:43:03 UTC (1,218 KB)
来源：arXiv cs.AI · arxiv.org