AI News HubLIVE
原文2 min read

SaliMory: Orchestrating Cognitive Memory for Conversational Agents

SALIMORY is a new framework that trains a single language model to manage cognitively-structured memory (user facts, preferences, working memory) for conversational agents, addressing the credit assignment bottleneck. Using hierarchical stage-wise process reward and reward-decomposed contrastive refinement, it supervises selective filtering, consolidation, and cue-driven recall end-to-end. It cuts memory-attributed failures by one-third, outperforms SOTA by over 10% in accuracy, and more than doubles the Good Personalization rate.

SourcearXiv Computational LinguisticsAuthor: 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

[2606.04120] SaliMory: Orchestrating Cognitive Memory for Conversational Agents

[Submitted on 2 Jun 2026]

Title:SaliMory: Orchestrating Cognitive Memory for Conversational Agents

View a PDF of the paper titled SaliMory: Orchestrating Cognitive Memory for Conversational Agents, by Kai Zhang and 13 other authors

View PDF HTML (experimental)

Abstract:Conversational agents that serve as lifelong companions must maintain persistent memory across all interactions. However, simply expanding context windows with raw retrieval degrades reasoning quality, while training memory agents via standard reinforcement learning creates a severe credit assignment bottleneck in a multi-stage pipeline. To solve this, we introduce SALIMORY, a framework that trains a single language model to manage a cognitively-structured memory-spanning user facts, preferences, and working memory. By introducing a hierarchical stage-wise process reward and reward-decomposed contrastive refinement, SALIMORY provides isolated supervision for distinct memory operations (selective filtering, consolidation, and cue-driven recall) end-to-end. SALIMORY cuts memory-attributed failures by one-third, outperforms the state-of-the-art by over 10% in end-to-end accuracy, and more than doubles the Good Personalization rate.

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

Cite as: arXiv:2606.04120 [cs.CL]

(or arXiv:2606.04120v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.04120

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Kai Zhang [view email] [v1] Tue, 2 Jun 2026 18:31:50 UTC (5,475 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled SaliMory: Orchestrating Cognitive Memory for Conversational Agents, by Kai Zhang and 13 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-06

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)