Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory
Graph structures are increasingly used in dialog memory systems, but empirical findings on their effectiveness remain inconsistent, making it unclear which design choices truly matter. We present an experimental, system-oriented analysis of long-term dialog memory architectures. We introduce a unified framework that decomposes dialog memory systems into core components and supports both graph-based and non-graph approaches. Under this framework, we conduct controlled, stage-wise experiments on LongMemEval and HaluMem, comparing common design choices in memory representation, organization, maintenance, and retrieval. Our results show that many performance differences are driven by foundational system settings rather than specific architectural innovations. Based on these findings, we identify stable and reliable strong baselines for future dialog memory research. Code are available at https://github.com/AvatarMemory/UnifiedMem
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Searching in Space and Time: Unified Memory-Action Loops for Open-World Object Retrieval
Service robots must retrieve objects in dynamic, open-world settings where requests may reference attributes ("the red mug"), spatial context ("the mug on the table"), or past states ("the mug that was here yesterday"). …
Temporal Model On Quantum Logic
This paper introduces a unified theoretical framework for modeling temporal memory dynamics, combining concepts from temporal logic, memory decay models, and hierarchical contexts. The framework formalizes the evolution …
modelUniMC: A Unified Framework for Long-Term Memory Conversation via Relevance Representation Learning
Open-domain long-term memory conversation can establish long-term intimacy with humans, and the key is the ability to understand and memorize long-term dialogue history information. Existing works integrate multiple mode…
Conversation SummarizationDecoderRepresentation LearningRetrievalA Unified Pre-training and Adaptation Framework for Combinatorial Optimization on Graphs
Combinatorial optimization (CO) on graphs is a classic topic that has been extensively studied across many scientific and industrial fields. Recently, solving CO problems on graphs through learning methods has attracted …
Combinatorial OptimizationDomain AdaptationMandol: An Agglomerative Agent Memory System for Long-Term Conversations
Long-term conversational agents need to remember and query cross-session, multi-typed information with complex correlations. Existing agent memory systems rely on heterogeneous vector and graph databases, which fragment …