mlsanityData to 14 Oct 2026

PersMem: Internalizing Personality into Dual-Pathway Memory for LLM Agents

arXiv 2609.34372 ↗First posted 28 Sep 2026cs.AIcited by 0

On the map: LLM agents and tool use → Agent memory systems also fits: Social simulation and multi-agent debate

Abstract (arXiv)

The profile of a role-playing agent usually depends on the pre-defined personality in a system prompt, whereas its memory processing pipeline, including prioritisation of stored memories and subsequent retrieval, remains independent of this personality. This separation causes the agent's memory processing to be inconsistent with the pre-defined personality, and makes it difficult to validate whether agent behaviours follow this personality. In this paper, we propose Personality-Integrated Memory (PersMem), which integrates personality into the agent's memory processing pipeline, making it consistently personality-dependent. PersMem processes memory using four steps, where the personality is mapped to operation-specific parameters controlling: (i) affective appraisal annotating emotion states of the user input; (ii) retention of previously stored memories along with the current input; (iii) passive affect-driven memory retrieval exploring memories similar to user input in semantics and personality-guided emotions; and (iv) active goal-driven memory retrieval that refines and selects passively retrieved memories for the reply. Consequently, consistency with the pre-defined personality can be examined by inspecting memory-processing traces during human-agent interactions. We evaluate these personality-dependent differences in attachment and Big Five settings. PersMem exceeds the chance baseline for four-way attachment classification by 23.1 percentage points. In Big Five dialogue comparisons, PersMem achieves 67.5% accuracy, 6.7 percentage points above a baseline using uniformly sampled memories. On CoSER, PersMem achieves an average score of 66.13, with scores of 69.33 for Character Fidelity and 84.33 for Storyline Quality. Together, these results show that PersMem produces distinguishable personality-related memory-processing patterns.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 30 of its 56 references that are in the map. First posted on arXiv 28 Sep 2026.

Builds on

30 of 56 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Memory OS of AI Agent30 May
  2. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  3. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialogue9 Jun
  4. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 26

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  3. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  4. 2025Persona Vectors: Monitoring and Controlling Character Traits in Language Modelscited by 345
  5. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 339
  6. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 234
  7. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  8. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  9. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 179
  10. 2023Personality Traits in Large Language Modelscited by 169
  11. 2024CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluationcited by 143
  12. 2024PersonaGym: Evaluating Persona Agents and LLMscited by 97
14 more
  1. 2025Consistently Simulating Human Personas with Multi-Turn Reinforcement Learningcited by 39
  2. 2025The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMscited by 36
  3. 2024Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions?cited by 34
  4. 2025Idiosyncrasies in Large Language Modelscited by 33
  5. 2025NRC VAD Lexicon v2: Norms for Valence, Arousal, and Dominance for over 55k English Termscited by 27
  6. 2024Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrievalcited by 26
  7. 2024Stick to your Role! Stability of Personal Values Expressed in Large Language Modelscited by 14
  8. 2026HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playingcited by 10
  9. 2025CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewardscited by 6
  10. 2026Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMscited by 5
  11. 2026ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessionscited by 5
  12. 2026Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societiescited by 2
  13. 2026AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writingcited by 2
  14. 2026Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agentscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents
  2. 2026ZifaMem: Structured Memory for Persona, Preference, and Emotional Continuity in AI Companions
  3. 2025Psychologically Enhanced AI Agents
  4. 2025Dynamic Affective Memory Management for Personalized LLM Agents
  5. 2026ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents
  6. 2026PTCBENCH: Benchmarking Contextual Stability of Personality Traits in LLM Systems
  7. 2026MemoryForge: Synthesize Lifelong Memory for Human-Like LLM Agents
  8. 2026Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data