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

• URL: http://arxiv.org/abs/2605.25693v1
• Date: Mon, 25 May 2026 10:48:24 GMT
• Title: From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
• Abstract summary: Current systems rely on persona-agnostic summarization, which records facts without persona-specific interpretation.<n>We introduce RoleMemo, a dataset featuring four reasoning tasks where the factual fragments must be interpreted through the persona to reach the correct answer.<n>We propose DualMem, which decouples memory into two streams: factual cognition and persona-conditioned insight.
• Score: 50.66268133366637
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 https://github.com/role2026/rolememo.

Related papers

• PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments [72.02445514666428]
  We introduce PERMA, a benchmark designed to evaluate persona consistency over time beyond static preference recall.<n>PerMA consists of temporally ordered interaction events spanning multiple sessions and domains, with preference-related queries inserted over time.<n> Experiments demonstrate that by linking related interactions, advanced memory systems can extract more precise preferences and reduce token consumption.
  arXiv  Detail & Related papers  (2026-03-24T14:04:11Z)
• D-Mem: A Dual-Process Memory System for LLM Agents [3.5426740232689604]
  We introduce D-Mem, a dual-process memory system.<n>It retains lightweight vector retrieval for routine queries while establishing an exhaustive Full Deliberation module as a high-fidelity fallback.<n>Experiments on the LoCoMo and RealTalk benchmarks using GPT-4o-mini and Qwen3-235B-Instruct demonstrate the efficacy of our approach.
  arXiv  Detail & Related papers  (2026-03-19T08:55:22Z)
• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents [49.63422082885992]
  We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents.<n>AdaMem organizes dialogue history into working, episodic, persona, and graph memories.<n>We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling.
  arXiv  Detail & Related papers  (2026-03-17T13:22:54Z)
• Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs [8.377003560888905]
  We propose the Memory-Driven Role-Playing paradigm.<n>Inspired by Stanislavski's "emotional memory" acting theory, this paradigm frames persona knowledge as the LLM's internal memory store.<n>We contribute: MREval, a fine-grained evaluation framework assessing four memory-driven abilities; MRPrompt, a prompting architecture that guides structured memory retrieval and response generation; and MRBench, a bilingual benchmark for fine-grained diagnosis.
  arXiv  Detail & Related papers  (2026-03-14T07:12:42Z)
• AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment [54.72137309071243]
  AlpsBench comprises 2,500 long-term interaction sequences curated from WildChat, paired with human-verified structured memories.<n>We define four pivotal tasks - personalized information extraction, updating, retrieval, and utilization - and establish protocols to evaluate the entire lifecycle of memory management.<n>Our benchmarking of frontier LLMs and memory-centric systems reveals that: (i) models struggle to reliably extract latent user traits; (ii) memory updating faces a performance ceiling even in the strongest models; (iii) retrieval accuracy declines sharply in the presence of large distractor pools; and (iv) while explicit memory mechanisms improve recall, they do not
  arXiv  Detail & Related papers  (2026-03-09T11:06:19Z)
• Learning Personalized Agents from Human Feedback [36.47803872623135]
  We introduce Personalized Agents from Human Feedback (PAHF), a framework for continual personalization.<n>PAHF learns online from live interaction using explicit per-user memory.<n> benchmarks quantify an agent's ability to learn initial preferences from scratch and subsequently adapt to persona shifts.
  arXiv  Detail & Related papers  (2026-02-18T04:18:47Z)
• PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory [56.81126490418336]
  Personalization is one of the next milestones in advancing AI capability and alignment.<n> PersonaMem-v2 simulates 1,000 realistic user-chatbot interactions on 300+ scenarios, 20,000+ user preferences, and 128k-token context windows.<n>We train Qwen3-4B to outperforms GPT-5, reaching 53% accuracy in implicit personalization.
  arXiv  Detail & Related papers  (2025-12-07T06:48:23Z)
• Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction [55.24448139349266]
  We present PAL-Bench, a new benchmark designed to evaluate the personalization capabilities of service-oriented assistants in long-term user-agent interactions.<n>To improve personalized service-oriented interactions, we propose H$2$Memory, a hierarchical and heterogeneous memory framework.
  arXiv  Detail & Related papers  (2025-11-17T14:22:32Z)
• Role-Aware Modeling for N-ary Relational Knowledge Bases [38.40941919126033]
  We propose a Role-Aware Modeling, RAM, for facts in n-ary relational KBs. RAM explores a latent space that contains basis vectors, and represents roles by linear combinations of these vectors. To this end, it presents a multilinear scoring function to measure the plausibility of a fact composed by certain roles and entities.
  arXiv  Detail & Related papers  (2021-04-20T06:37:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.