NapMem is introduced, a framework for learning to use long-term user memory as a structured action space rather than passively retrieved context, and suggests that long-term user memory benefits from coupling structured storage with a learned policy for using memory at the appropriate granularity.
Abstract
Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfaces, making the model a consumer of pre-selected evidence. We introduce NapMem, a framework for learning to use long-term user memory as a structured action space rather than passively retrieved context. NapMem organizes user history into a linked multi-granularity memory pyramid, where raw conversations, typed memory records, topic tracks, and user profiles are connected through provenance relations, and exposes these levels through memory tools. The agent is trained to select memory according to the query and intermediate evidence, allowing it to inspect different memory granularities before answering. Experiments on PersonaMem-v2, LongMemEval, and LoCoMo show that a NapMem agent trained with memory-tool reinforcement learning is competitive across diverse memory-intensive tasks, while evaluations on non-memory tasks suggest that the learned policy largely preserves general reasoning and tool-use abilities. Additional analyses examine storage, inference cost, tool-use behavior, and ablations over navigation, memory granularity, and RL training. Our results suggest that long-term user memory benefits from coupling structured storage with a learned policy for using memory at the appropriate granularity.
RippleMem is a long-term memory system that replaces one-shot retrieval with adaptive associative recollection, Inspired by cue-dependent episodic retrieval and associative completion, that stores interaction history as cue-rich episodic memory units and organizes them in an event-centric memory graph.
Jingbo Ji, Lingyi Li, Xilong Cheng et al.· 0 citations
This paper presents AdaMM, a framework that jointly supports retrieval and analytic memory that extracts provenance-linked attribute-value observations from dialogue, images, and contextual metadata, discovers recurring field structures, and materializes them for analytical access.
Zhoujin Tian, Hao Zhang, Yao Tian et al.· 0 citations
This work proposes a novel Human-profile Enhanced Retrieval Optimization framework for long-term agent memory (HERO), which converts the dialogue history into a traceable heterogeneous memory graph that preserves raw dialogue text as evidence for reasoning, thereby mitigating information loss.
Yuanhua Lin, Yile Li, Zhiyuan Zhao et al.· 0 citations
TrajWiki is proposed, a trajectory-based memory framework for long-horizon conversational agents that improves long-horizon dialogue performance across both open-source and closed-source LLM backbones, while providing greater interpretability and diagnostic visibility into memory evolution, retrieval failures, and answer generation.
Jingyu Sun, Yuyang Xue, Mingyang Li et al.· 0 citations
Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memories to reflective insight stores, access memory through fixed, hand-designed heuristics. We argue that this static view of memory is a core bottleneck for agentic learning because optimal memory behavior is fundamentally context-dependent. The early stages of the tasks, benefit from minimal retrieval because memory is sparse; recurring goal types benefit from plan reuse rather than generic nearest-neighbor lookup; stuck agents benefit from re-retrieval with alternative queries; and across long task streams, the memory store itself must be consolidated and pruned to remain useful. We present Memory as a Controlled Process (MemCon), a framework that models memory operations as a Markov Decision Process and learns an online policy that adaptively decides when, what, and how much to retrieve, when to inject a distilled plan, and when to consolidate or forget. MemCon is backend-agnostic: it wraps any existing memory implementation, learns from task-by-task binary feedback with no pretraining and no additional LLM calls, and uses a lightweight tabular contextual bandit with UCB exploration that converges within tens of tasks. Across 6 benchmarks, 3 agent frameworks, and 3 LLM backbones, MemCon consistently outperforms multiple memory baselines by up to 15.2 points in task success while reducing token consumption by 5--20%.
Eric Jiang, Zhi Zhang, Yuchen Wu et al.· 1 citation
