The Past Is Prologue: A Plug-in Controller for Selective Updates in Sequentially Evolving LLM Memory

2026-06-30

AI Summary

This work addresses the limitations of existing memory systems in large language models during sequential learning, where blindly accepting all local memory updates often leads to overwriting useful knowledge, over-specialization of rules, or recency bias. To mitigate these issues, the authors propose Janus, a plug-and-play memory controller that intelligently decides whether to accept candidate memory updates without altering the underlying update mechanism. Janus introduces a Memory Momentum Trigger to detect anomalous memory trajectories and leverages a lightweight hybrid evaluation set—constructed from coverage, boundary, and new-task samples—to efficiently compare the quality of old and new memories without replaying historical data. Experiments demonstrate that Janus consistently improves accuracy by 2.7–4.6 percentage points across six datasets, two large language models, and two memory updaters.

Abstract

Sequentially evolving LLM memory enables agents to reuse past experience, but existing systems usually deploy each locally generated memory update without checking whether it improves future behavior. As a result, updates that help the current task may overwrite useful knowledge, introduce over-specific rules, or bias the final memory toward recent examples. We propose Janus, a plug-in memory controller that decides whether to accept a candidate memory update or retain the previous memory. To make this decision efficient, Janus uses a Memory Momentum Trigger to identify suspicious deviations in the memory-update trajectory, and compares old and new memories on a compact hybrid evaluation set of coverage, boundary, and fresh tasks instead of replaying the full history. Janus is method-agnostic and wraps existing updaters without changing their update rules. Across six datasets, two backbone LLMs, and two memory updaters, Janus improves average accuracy by +2.7 to +4.6 points over the corresponding base updaters.

Problem

• sequential memory update
• memory overwrite
• knowledge bias
• LLM memory evolution
• selective update

Innovation

• selective memory update
• memory momentum trigger
• hybrid evaluation set
• plug-in controller
• sequentially evolving LLM memory