RGMem: Renormalization Group-based Memory Evolution for Language Agent User Profile

TL;DR

RGMem addresses the challenge of cross-session user profiling in LLM-based systems by introducing a renormalization-group inspired framework that evolves memory across micro, meso, and macro scales. It formalizes memory as a variational problem with an effective Hamiltonian and implements three RG operators to progressively coarse-grain evidence into stable, high-level user traits, allowing dynamic shifts via phase transitions. Empirical results on LOCOMO show RGMem substantially outperforms retrieval-based baselines and approaches full-context upper bounds, with ablations confirming the critical role of the microscopic and mesoscopic layers and the parameterized flow. The framework offers auditable, scalable, and interpretable memory evolution for language agents, with potential insights into universal patterns governing memory and self-concept dynamics in interactive AI.

Abstract

Personalized and continuous interactions are the key to enhancing user experience in today's large language model (LLM)-based conversational systems, however, the finite context windows and static parametric memory make it difficult to model the cross-session long-term user states and behavioral consistency. Currently, the existing solutions to this predicament, such as retrieval-augmented generation (RAG) and explicit memory systems, primarily focus on fact-level storage and retrieval, lacking the capability to distill latent preferences and deep traits from the multi-turn dialogues, which limits the long-term and effective user modeling, directly leading to the personalized interactions remaining shallow, and hindering the cross-session continuity. To realize the long-term memory and behavioral consistency for Language Agents in LLM era, we propose a self-evolving memory framework RGMem, inspired by the ideology of classic renormalization group (RG) in physics, this framework enables to organize the dialogue history in multiple scales: it first extracts semantics and user insights from episodic fragments, then through hierarchical coarse-graining and rescaling operations, progressively forms a dynamically-evolved user profile. The core innovation of our work lies in modeling memory evolution as a multi-scale process of information compression and emergence, which accomplishes the high-level and accurate user profiles from noisy and microscopic-level interactions.

Figures (3)

• Figure 1: A comparative illustration of memory models encountering the multi-scale Challenge.
• Figure 2: Overview of RGMem Framework.
• Figure 3: Parameter sensitivity analysis for RGMem's retrieval and dynamics parameters.