AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
Abstract
AdaMem is an adaptive memory framework for dialogue agents that organizes conversation history into multiple memory types and uses conditional retrieval to improve long-horizon reasoning and user modeling.
Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step reasoning. However, existing memory systems still face three core challenges: they often rely too heavily on semantic similarity, which can miss evidence crucial for user-centric understanding; they frequently store related experiences as isolated fragments, weakening temporal and causal coherence; and they typically use static memory granularities that do not adapt well to the requirements of different questions. We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents. AdaMem organizes dialogue history into working, episodic, persona, and graph memories, enabling the system to preserve recent context, structured long-term experiences, stable user traits, and relation-aware connections within a unified framework. At inference time, AdaMem first resolves the target participant, then builds a question-conditioned retrieval route that combines semantic retrieval with relation-aware graph expansion only when needed, and finally produces the answer through a role-specialized pipeline for evidence synthesis and response generation. We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling. Experimental results show that AdaMem achieves state-of-the-art performance on both benchmarks. The code will be released upon acceptance.
Community
good paper!
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning (2026)
- AMA: Adaptive Memory via Multi-Agent Collaboration (2026)
- Choosing How to Remember: Adaptive Memory Structures for LLM Agents (2026)
- M2A: Multimodal Memory Agent with Dual-Layer Hybrid Memory for Long-Term Personalized Interactions (2026)
- Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation (2026)
- BMAM: Brain-inspired Multi-Agent Memory Framework (2026)
- E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper