SRCoT 架构提出：检索-反思-修订闭环让本地 LLM 生成带证据标注的文本
Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs
arXiv 上一篇新论文，提出 SRCoT 闭环架构，让本地跑的小模型输出每句话都能溯源到证据，代码思路值得借鉴。
论文提出 Self-Reflective Chain-of-Thought（SRCoT），一种将文本生成组织为检索-反思-修订闭环的模块化架构。它将环境状态、持久知识、经验与短期记忆分离到带溯源标签的存储中，用 BM25 检索提供本地上下文，中间草稿、缺口标记和声明-证据映射会反馈到后续的修订或弃答决策。作者在急救医疗服务和 Munich-Sim 应急模拟两个全合成场景中做了基于轨迹的案例研究，原型在配备 128 GB 内存的 Apple M4 笔记本上本地运行。轨迹分析显示溯源标注错误、证据覆盖不全等问题依然存在，作者明确声明该工作不主张降低幻觉或具备临床有效性。
Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs
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.
