Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs
Read the original on arXiv AI →Self-Reflective Chain-of-Thought (SRCoT) is a modular architecture that structures text generation as a closed Retrieve–Reflect–Revise loop, separating environment state, persistent knowledge, accumulated experience, and short-term memory into provenance-labeled stores. BM25 retrieval supplies local context, while subsequent passes expose intermediate drafts, missing-information markers, follow-up queries, and optional claim–evidence mappings to inform retrieval, revision, clarification, or abstention decisions. The authors demonstrate the approach in synthetic emergency medical and simulation scenarios, showing source-labeled documentation, explicit gap marking, and structured dispatch-style outputs, while also noting provenance-assignment errors, incomplete evidence coverage, and unsafe assumptions that persist despite prompting constraints.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.