Inside Out: Evolving User-Centric Core Memory Trees for Long-Term Personalized Dialogue Systems

ACL ARR 2026 January Submission3672 Authors

Keywords: PersonaTree, Memory, Long-term personalized dialogue, Reinforcement learning, MemListener

Abstract: Existing long-term personalized dialogue systems struggle to reconcile unbounded interaction streams with finite context constraints, often succumbing to memory noise accumulation, reasoning degradation, and persona inconsistency. To address these challenges, this paper proposes Inside Out, a framework that utilizes a globally maintained PersonaTree as the carrier of long-term user profiling. By constraining the trunk with an initial schema and updating the branches and leaves, PersonaTree enables controllable growth, achieving memory compression while preserving consistency. Moreover, we train a lightweight MemListener via reinforcement learning with process-based rewards to produce structured, executable, and interpretable {ADD, UPDATE, DELETE, NO_OP} operations, thereby supporting the dynamic evolution of the personalized tree. During response generation, PersonaTree is directly leveraged to enhance outputs in latency-sensitive scenarios; when users require more details, the agentic mode is triggered to introduce details on-demand under the constraints of the PersonaTree. Experiments show that PersonaTree outperforms full-text concatenation and various personalized memory systems in suppressing contextual noise and maintaining persona consistency. Notably, the small MemListener model achieves memory-operation decision performance comparable to, or even surpassing, powerful reasoning models such as DeepSeek-R1-0528 and Gemini-3-Pro.

Paper Type: Long

Research Area: Dialogue and Interactive Systems

Research Area Keywords: Grounded dialog, Knowledge augmented, Human-AI interaction

Contribution Types: NLP engineering experiment

Languages Studied: The proposed method is language-agnostic and is not limited to a specific language.

Submission Number: 3672