Signals 4 · free daily AI digest

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

Paper recorded by Signals 4 on 2026-11-02 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-11-02 on arXiv · recorded by Signals 4 on 2026-11-03

Category: cs.CL · 自然语言处理 · first seen 2026-11-03

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 construct

Read on arXiv →

#32 most recent of 628 cs.CL papers we have recorded · ↑ newer: Same Sentence, Different Construct: Identity-Swapped Rationales Reveal · ↓ older: GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Wea
Cite this page: Chain on Demand: Deferred Evidence Organization for Long-Term Conversational Memory: the #32 most recent of 628 cs.CL papers we have recorded (as of 2026-11-02). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/chain-on-demand-deferred-evidence-organization-for-long-term-conversational-memo.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions