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

TL;DR

AdaMem introduces an adaptive, user-centric memory system for long-horizon dialogue agents, improving reasoning and personalization by combining structured memories and dynamic retrieval strategies.

Contribution

It proposes a novel memory framework that organizes dialogue history into multiple memory types and employs adaptive retrieval, advancing long-term reasoning and user modeling.

Findings

Achieves state-of-the-art results on LoCoMo and PERSONAMEM benchmarks.

Effectively combines semantic retrieval with relation-aware graph expansion.

Enhances long-horizon reasoning and user personalization in 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.