SPIN Unprocessed
Source arXiv Computation and Language export.arxiv.org Analyst
July 30, 2026 ai_technology research

CMT-RAG: Complementary Memory Traces for Multi-turn Multi-hop RAG

View original on arxiv.org

Overview

arXiv:2607.26470v1 Announce Type: new Abstract: Multi-turn information-seeking conversations require both multi-hop reasoning and long-range dependency tracking across turns. However, existing RAG systems typically represent conversational memory as raw dialogue history, rewritten queries, or unstructured summaries, making it difficult to recover the specific prior reasoning steps and evidence required for follow-up queries. Our key insight is to align conversational memory with retrieval by rep

SpinGraph analysis pending — check back after processing.

Ask AI about this story

Opens with the SpinGraph .md URL and structured context — one click, prompt included.

More from arXiv Computation and Language

View all →

Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO