Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

Shannan Yan, Jingchen Ni, Leqi Zheng, Jiajun Zhang, Peixi Wu, Dacheng Yin, Jing Lyu, Chun Yuan, Fengyun Rao

Abstract

Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step reasoning. However, existing memory systems still face three core challenges: they often rely too heavily on semantic similarity, which can miss evidence crucial for user-centric understanding; they frequently store related experiences as isolated fragments, weakening temporal and causal coherence; and they typically use static memory granularities that do not adapt well to the requirements of different questions. We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents. AdaMem organizes dialogue history into working, episodic, persona, and graph memories, enabling the system to preserve recent context, structured long-term experiences, stable user traits, and relation-aware connections within a unified framework. At inference time, AdaMem first resolves the target participant, then builds a question-conditioned retrieval route that combines semantic retrieval with relation-aware graph expansion only when needed, and finally produces the answer through a role-specialized pipeline for evidence synthesis and response generation. We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling. Experimental results show that AdaMem achieves state-of-the-art performance on both benchmarks. The code will be released upon acceptance.

AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

Abstract

Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step reasoning. However, existing memory systems still face three core challenges: they often rely too heavily on semantic similarity, which can miss evidence crucial for user-centric understanding; they frequently store related experiences as isolated fragments, weakening temporal and causal coherence; and they typically use static memory granularities that do not adapt well to the requirements of different questions. We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents. AdaMem organizes dialogue history into working, episodic, persona, and graph memories, enabling the system to preserve recent context, structured long-term experiences, stable user traits, and relation-aware connections within a unified framework. At inference time, AdaMem first resolves the target participant, then builds a question-conditioned retrieval route that combines semantic retrieval with relation-aware graph expansion only when needed, and finally produces the answer through a role-specialized pipeline for evidence synthesis and response generation. We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling. Experimental results show that AdaMem achieves state-of-the-art performance on both benchmarks. The code will be released upon acceptance.
Paper Structure (71 sections, 4 equations, 5 figures, 8 tables)

This paper contains 71 sections, 4 equations, 5 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Limitation 1:
  3. Limitation 2:
  4. Limitation 3:
  5. Related Works
  6. Agentic Memory
  7. Multi-Agent LLMs
  8. Approach
  9. Method Overview
  10. Memory Construction
  11. Message understanding and normalized write.
  12. Working-to-episodic consolidation.
  13. Topic regrouping, persona refresh, and graph synchronization.
  14. Question-Conditioned Retrieval
  15. Target participant resolution.
  16. ...and 56 more sections

Figures (5)

  • Figure 1: Comparison of previous methods and AdaMem. Conventional approaches rely on fixed-length chunks or coarse summaries with semantic retrieval, while AdaMem emphasizes user-centric adaptive structured memories and multi-agent collaborative retrieval.
  • Figure 2: Model overview. Dialogue history is organized into working, episodic, persona, and graph memories, and question answering is performed through target-aware, question-conditioned retrieval and role-specialized evidence synthesis.
  • Figure 3: Ablation on key hyperparameters.
  • Figure 4: Case One (Success).
  • Figure 5: Case Two (Failure).