Bi-Mem: Bidirectional Construction of Hierarchical Memory for Personalized LLMs via Inductive-Reflective Agents

TL;DR

Bi-Mem introduces a bidirectional hierarchical memory framework for personalized LLMs, combining inductive and reflective agents to improve memory fidelity and question answering in long-term conversations.

Contribution

It presents a novel bidirectional memory construction method with inductive and reflective agents to enhance global-local memory alignment in personalized LLMs.

Findings

Significant improvements in question answering accuracy on personalized tasks.

Effective mitigation of memory hallucinations and noise amplification.

Enhanced global-local memory consistency through the proposed calibration mechanism.

Abstract

Constructing memory from users' long-term conversations overcomes LLMs' contextual limitations and enables personalized interactions. Recent studies focus on hierarchical memory to model users' multi-granular behavioral patterns via clustering and aggregating historical conversations. However, conversational noise and memory hallucinations can be amplified during clustering, causing locally aggregated memories to misalign with the user's global persona. To mitigate this issue, we propose Bi-Mem, an agentic framework ensuring hierarchical memory fidelity through bidirectional construction. Specifically, we deploy an inductive agent to form the hierarchical memory: it extracts factual information from raw conversations to form fact-level memory, aggregates them into thematic scenes (i.e., local scene-level memory) using graph clustering, and infers users' profiles as global persona-level memory. Simultaneously, a reflective agent is designed to calibrate local scene-level memories using global constraints derived from the persona-level memory, thereby enforcing global-local alignment. For coherent memory recall, we propose an associative retrieval mechanism: beyond initial hierarchical search, a spreading activation process allows facts to evoke contextual scenes, while scene-level matches retrieve salient supporting factual information. Empirical evaluations demonstrate that Bi-Mem achieves significant improvements in question answering performance on long-term personalized conversational tasks.