Paper

SaliMory: Orchestrating Cognitive Memory for Conversational Agents

Unreadunread

AI summary

arXiv:2606. 04120v1 Announce Type: new Abstract: Conversational agents that serve as lifelong companions must maintain persistent memory across all interactions.

Reading status

Priority

About this paper

Authors: Kai Zhang, Xinyuan Zhang, Hongda Jiang, Shiun-Zu Kuo, Hyokun Yun, Ejaz Ahmed, Shereen Oraby, Ziyun Li, Sanat Sharma, Ann Lee, Ahmed A Aly, Anuj Kumar, Raffay Hamid, Xin Luna Dong
Released: 2026-06-04 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because SaliMory: Orchestrating Cognitive Memory for Conversational Agents overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, persona, good, eval, line, rate, stage, language. Source: arxiv cs.CL (NLP).
arXiv: 2606.04120

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to SaliMory: Orchestrating Cognitive Memory for Conversational Agents. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.