cs.CLNov 2, 2026

Chain on Demand: Deferred Evidence Organization for Long-Term Conversational Memory

Authors: Di Lu, Zechen Li, Hao Xue

Organizations: University of New South Wales, Sydney · Hong Kong University of Science and Technology (Guangzhou) · Hong Kong University of Science and Technology

Abstract

Long-term conversational memory faces a timing mismatch: write-time summaries and graphs organize history before a future query is known, while independent retrieval can allocate a limited evidence budget to redundant or fragmented turns. We introduce Chain on Demand (CoD), a query-time evidence organization framework over an unchanged turn-level memory. Given a broad candidate pool, CoD constructs a temporary evidence chain by allocating a fixed anchor budget according to query relevance, lexical diversity relative to selected anchors, and newly covered query terms, followed by deterministic restoration of each selected anchor's same-session neighborhood. The resulting chain is used only for the current query, while the underlying conversational memory remains unchanged. In a paired comparison over all 1,986 LoCoMo questions, CoD achieves 82.2% accuracy on 1,540 non-adversarial questions and 76.3% on all 1,986 questions. On LongMemEval-S, one fixed configuration that indexes both user and assistant turns obtains 86.6% across all 500 questions. These results show that long-term memory can preserve the original conversation while deferring evidence organization until the information need is known.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. JustMem: Just-Enough Memory Access for Long-Term Conversations

    Sep 17, 2026Guanhua Chen, Yanting Wang, Wenjing Zhi +1Conversational MemoryConversational QA

  2. EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory

    Apr 30, 2026Yuyang Li, Yime He, Zeyu Zhang +1Temporal IREvidence Retrieval

  3. APDMem: Agent-Controlled Progressive Disclosure for Query-Adaptive Long-Term Memory

    Oct 1, 2026Chin-Lun Fu, Anagha Kulkarni, Hong Ni +1Long-Term Conversational MemoryStructured Memory for LLM Agents