arXiv cs.AI· Fabian Broszio, Michael Hoffmann, Adrian Paschke·· 12 小时前AI 评分26
SRCoT：在边缘 LLM 上通过检索-反思-修订闭环实现基于证据的文本生成
Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs
AI 导读
研究者提出 Self-Reflective Chain-of-Thought（SRCoT），将生成组织为检索-反思-修订的闭环流程，把环境状态、持久知识、积累经验与短期记忆分存于带来源标注的存储中，由 BM25 检索提供本地上下文。
正文 · 原文
Abstract:Large language models (LLMs) can generate fluent outputs that lack source support or conflict with local operational constraints. We introduce Self-Reflective Chain-of-Thought (SRCoT), a modular architecture that organizes generation as a closed Retrieve--Reflect--Revise loop. SRCoT separates environment state, persistent knowledge, accumulated experience, and short-term memory into provenance-labeled stores. BM25 retrieval supplies local context; subsequent passes expose intermediate drafts, missing-information markers, follow-up queries, and optional claim--evidence mappings. These artifacts inform retrieval, revision, clarification, or abstention decisions. We examine the architecture through qualitative, trace-based case studies in two fully synthetic settings: emergency medical services and Munich-Sim, an emergency-operations simulation. Local prototype runs on an Apple M4-family laptop with 128 GB memory illustrate source-labeled documentation, explicit gap marking, and structured dispatch-style outputs. The traces also reveal provenance-assignment errors, incomplete evidence coverage, and unsafe assumptions that remain possible despite prompting constraints. These cases demonstrate report-level inspectability and local execution, not comparative superiority, hallucination reduction, clinical validity, or operational safety. The architecture separates retrieval and control from the model interface, but behavior across different models remains to be evaluated. SRCoT is a research proof of concept requiring human review, with its principal contribution lying in an inspectable control procedure rather than a new model.
| Comments: | 28 pages, 2 figures. Extended technical account; a related brief report based on overlapping work has been submitted to Frontiers in Disaster and Emergency Medicine. The two manuscripts do not represent independent empirical studies |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.23311 [cs.AI] |
| (or arXiv:2610.23311v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.23311 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fabian Broszio [view email]
[v1]
Fri, 16 Oct 2026 11:14:52 UTC (582 KB)
来源：arXiv cs.AI · arxiv.org