The proposed REALM framework models long-term memory as a continual lifecycle by autonomously organizing memories into a heterogeneous cognitive graph, retrieving evidence via adaptively composed graph-search atoms, and continually reconsolidating memories based on retrieval feedback.
Abstract
Long-term memory is essential for LLM-based agents operating over extended interactions. Existing memory systems primarily update memory when new information arrives, treating retrieval as the endpoint of memory access rather than a driver of memory evolution. Consequently, retrieval feedback is rarely exploited to reorganize memory for future access continuously. Moreover, most existing approaches rely on predefined memory structures together with fixed retrieval pipelines, limiting the agent's ability to organize and evolve its own memory autonomously. Inspired by memory reconsolidation in cognitive neuroscience, we propose \textbf{REALM}, a \textbf{r}econsolidation-\textbf{e}volution \textbf{a}gentic \textbf{l}ong-term \textbf{m}emory framework. It models long-term memory as a continual lifecycle by autonomously organizing memories into a heterogeneous cognitive graph, retrieving evidence via adaptively composed graph-search atoms, and continually reconsolidating memories based on retrieval feedback. REALM achieves an average accuracy of 75.97\% on LoCoMo and 65.11\% on LongMemEval, outperforming the strongest baselines by 7.17 and 1.31 points respectively. Ablation studies confirm that memory reconsolidation consistently boosts performance, with further analyses revealing that it progressively reorganizes related memory units into more coherent local structures for collective evidence recall and utilization during reasoning. These results suggest that retrieval-driven memory reconsolidation provides an effective mechanism for continually evolving long-term memory in LLM agents.
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, Xi-Long Cheng et al.· 2 citations
RIME is introduced, a retrieval-induced memory framework that shifts memory construction from monolithic compression toward evidence-centered integration and consistently achieves the best performance across all three quality metrics among the compared methods, while requiring substantially fewer query-time LLM tokens.
Wan-Qi Zhou, Jia-Wei Lu, Yang Wang et al.· arXiv.org· 0 citations
Experiments on LoCoMo and MemConflict demonstrate that the proposed EMIR framework and intent-guided multi-round retrieval mechanism improves long-term memory utilization, dynamic and static conflict handling, and complex retrieval performance, achieving relative improvements of more than 12\% in certain categories.
Jin-Lan Liu, Hong-Liang Sun, Yong Wang et al.· 0 citations
MindMemOS is presented, a portable and self-evolving memory operating layer that organizes open-world information using a unified entity property timestructure that supports scenario-adaptive memory modeling, higher-order pattern discovery, autonomous memory refinement, and continuous skill evolution.
Kaichao Liang, Yu-Qi Cui, Hao Kong et al.· 0 citations
Dual-Layer Agentic Memory is proposed, a framework that shifts memory management to the write phase through cost-aware epistemic routing and periodic parametric consolidation, allowing the router to adaptively suppress redundant writes as the model's epistemic boundaries evolve.
Wen-Zhi Li, Dong Nie, Ruiyi Lan et al.· 1 citation