Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents
Yuanyi Song, Weinan Zhang and colleagues (SJTU, OPPO) propose REALM, an agent memory that reorganizes its graph structure based on which memories are retrieved and used together.
Ask this paper
Organization: Memories form a heterogeneous cognitive graph built by the agent itself.
Retrieval: Evidence is gathered by composing graph-search strategy atoms: seed localization, adaptive expansion and aggregation.
Reconsolidation: After retrieval, confidence-guided local topology updates link memories that were used together.
Results: 75.97% average accuracy on LoCoMo and 65.11% on LongMemEval, 7.17 and 1.31 points above the strongest baselines; ablations confirm reconsolidation helps.
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.