资讯

From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents

📅 2026-11-16 · AI导航编辑部
Computer Science > Computation and Language [Submitted on 25 May 2026 (v1), last revised 13 Nov 2026 (this version, v2

Computer Science > Computation and Language

[Submitted on 25 May 2026 (v1), last revised 13 Nov 2026 (this version, v2)]

Title:From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents

View PDF HTML (experimental)Abstract:While role-playing agents excel in short-term interactions, long-term conversations overwhelm context windows, motivating external memory frameworks. Current systems typically rely on persona-agnostic summarization, which records facts without persona-specific interpretation, yielding generic responses that compromise persona fidelity. To bridge this gap, we introduce RoleMemo, a dataset featuring four reasoning tasks where the factual fragments must be interpreted through the persona to reach the correct answer. Evaluation on RoleMemo exposes critical limitations of persona-agnostic frameworks. We thus propose DualMem, which decouples memory into two streams: factual cognition and persona-conditioned insight. Trained through Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), our framework with a 4B-parameter model outperforms zero-shot persona-agnostic frameworks powered by DeepSeek-V3.2 for sustained persona fidelity. Our resources are available at this https URL.

Submission history

From: Ruofan Hu [view email][v1] Mon, 25 May 2026 10:48:24 UTC (1,553 KB)

[v2] Fri, 13 Nov 2026 03:33:34 UTC (1,542 KB)

Additional Features

Current browse context:

cs.CL

References & Citations

Loading...

Bibliographic and Citation Tools

Bibliographic Explorer (What is the Explorer?)

Connected Papers (What is Connected Papers?)

Litmaps (What is Litmaps?)

scite Smart Citations (What are Smart Citations?)

Code, Data and Media Associated with this Article

alphaXiv (What is alphaXiv?)

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub (What is DagsHub?)

Gotit.pub (What is GotitPub?)

Hugging Face (What is Huggingface?)

ScienceCast (What is ScienceCast?)

Demos

Recommenders and Search Tools

Influence Flower (What are Influence Flowers?)

CORE Recommender (What is CORE?)

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.

来源:https://arxiv.org/abs/2605.25693