AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

Shannan Yan; Jingchen Ni; Leqi Zheng; Jiajun Zhang; Peixi Wu; Dacheng Yin; Jing Lyu; Chun Yuan

cs.CLMar 17, 2026

AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

Authors: Shannan Yan, Jingchen Ni, Leqi Zheng, Jiajun Zhang, Peixi Wu, Dacheng Yin, Jing Lyu, Chun Yuan,

Organizations: Tsinghua University · WeChat Vision, Tencent Inc.

Abstract

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.

Figures & tables

Figure 1: Comparison of previous methods and AdaMem. Conventional approaches rely on fixed-length chunks or coarse summaries with semantic retrieval, while AdaMem emphasizes user-centric adaptive structured memories and multi-agent collaborative retrieval.

Figure 2: Model overview. Dialogue history is organized into working, episodic, persona, and graph memories, and question answering is performed through target-aware, question-conditioned retrieval and role-specialized evidence synthesis.

Model	Method	Multi-hop		Temporal		Open Domain		Single-hop		Overall
Model	Method	F1	BLEU-1	F1	BLEU-1	F1	BLEU-1	F1	BLEU-1	F1	BLEU-1
GPT-4.1-mini	MemGPT	10.35	10.26	30.06	24.03	28.35	23.49	22.95	17.10	22.50	17.64
	A-Mem	11.16	11.07	42.30	33.75	30.69	25.38	24.84	18.54	26.37	20.70
	Mem0	35.19	26.55	34.38	29.07	20.88	15.57	42.66	36.90	38.16	32.04
	LangMem	36.45	28.53	42.57	35.91	28.80	23.13	44.82	38.25	41.76	35.10
	Zep	26.73	17.91	20.97	17.55	21.24	16.92	39.96	35.10	32.40	27.09

Table 1: Performance on the LoCoMo benchmark. The best performance is highlighted in bold , and the second-best is underlined .

Method	Recall user shared facts	Suggest new ideas	Track full preference evolution	Revisit reasons behind preference updates	Provide preference- aligned recommendations	Generalize to new scenarios	Average
A-Mem	63.01	27.96	54.68	85.86	69.09	57.89	59.75
Mem0	32.13	15.05	54.68	80.81	52.73	57.89	48.55
LangMem	31.29	24.73	53.24	81.82	40.00	8.77	40.64
AdaMem	67.81	21.51	61.15	89.90	65.45	73.68	63.25

Table 2: Performance on the PERSONAMEM benchmark.

Configuration	Graph	Fusion	Multi-agent	F1	BLEU-1
AdaMem (full)	✓	✓	✓	44.65	37.92
w/o graph	✗	✓	✓	42.63	35.85
w/o fusion	✓	✗	✓	42.77	36.26
w/o multi-agent	✓	✓	✗	43.24	36.34

Table 3: Ablation on key components.

Model	Multi-hop		Temporal		Open Domain		Single-hop		Overall
Model	F1	BLEU-1	F1	BLEU-1	F1	BLEU-1	F1	BLEU-1	F1	BLEU-1
GPT-4o-mini	35.18	26.32	51.49	37.06	25.82	21.46	42.21	36.43	41.84	33.78
GPT-4.1-mini	37.70	32.08	55.90	42.37	25.87	21.70	44.84	40.02	44.65	37.92
Qwen3-4B-Instruct	29.50	23.35	40.45	29.74	20.05	17.68	39.74	34.98	36.78	30.68
Qwen3-30B-A3B-Instruct	30.82	25.17	43.51	30.90	26.55	23.31	40.68	35.99	38.58	32.16

Table 4: Ablation on model sizes.

Figure 3: Ablation on key hyperparameters.

Method	F1	BLEU-1	Tokens	Latency (s)
A-Mem	26.37	20.70	2720	3.227
Mem0	38.16	32.04	1340	3.739
Zep	32.40	27.09	2461	3.255
AdaMem	44.65	37.92	2248	4.722

Table 5: Performance-efficiency trade-off.

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Edge type	Weight
mentions	0.75
supports	0.90
same_topic	0.55
temporal_next	0.70
speaker_related	0.60

Appendix

Table 6: Default retrieval-time edge priors.

Weight	Value
$\alpha$ semantic rank	0.7
$\beta$ graph rank	0.1
$\gamma$ recency	0.1
$\delta$ fact confidence	0.1

Appendix

Table 7: Default fusion prior in the benchmark configuration.

Setting	Value
Working-memory capacity $C_{\mathrm{w}}$	20
Consolidation segment length $r$	5
Baseline retrieval top- $K$	10
Fact reactivation threshold $\tau_{\mathrm{drop}}$	0.1
Base graph hop depth	1
Base graph seed count	2

Appendix

Table 8: Representative released benchmark defaults.

LLM Agent Memory

Large language model agent memory lets agents retain, organize, retrieve, and update information across interactions and long-running tasks.

See all 373 papers

AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agents
Jun 19, 2026Xingyu Chen, Rui Wang, Zhaopeng Tu +1LLM Agent Memory Persistent Memory for Language Models
Shanghai Jiao Tong University, Tencent · Shanghai Jiao Tong University · Tencent
LeanMem: Simple and Efficient Long-Term Memory for LLM Agents
Aug 4, 2026Yuxin Liao, Le Wu, Min Hou +3LLM Agent Memory Persistent Memory for Language Models
Hefei University of Technology
TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents
Aug 2, 2026Jingyu Sun, Yuyang Xue, Mingyang Li +9Agent Memory LLM Agent Memory
1The University of Manchester · 2The University of Melbourne · 3The University of Edinburgh +2

Jun 19, 2026J/K move · Enter open · S save

AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agents

Xingyu Chen, Rui Wang, Zhaopeng Tu, Liefeng Bo

Shanghai Jiao Tong University, Tencent · Shanghai Jiao Tong University · Tencent

LLM Agent Memory Persistent Memory for Language Models Agent Memory Management Personal AI Agents Memory Management for LLM Agents

Open paper AskPDF arXiv

Long-term memory systems allow LLM agents to preserve information beyond a single context window, but most systems focus on storing and retrieving facts after extraction, leaving the write decision under-specified. What deserves memory can depend on the user's current task, topic, activity, or interaction partner, while uniform extraction applies one notion of importance across these different situations. We formulate this challenge as preference-conditioned write control and introduce AdaMem, which uses adaptive natural-language Memory Policies to personalize what an agent writes to memory. Each policy represents the user's memory preference for a particular interaction context, is updated from periodic feedback, and controls subsequent memory writing. We evaluate this loop in AdaMem-Bench, which assigns different memory preferences to six concurrent interaction personas across five ten-week stories. Across two extraction models and two feedback modes, AdaMem improves average QA accuracy over Mem0 from 80.0% to 84.35% while reducing persistent memory by 9.27%. Our analyses show that explicit feedback helps models learn better memory policies, but current models still struggle to translate those policies into reliably selective writing behavior. AdaMem thus demonstrates the promise of adaptive write control while exposing policy execution as a central limitation of current memory agents. Our code is publicly available: https://github.com/galaxyChen/AdaMem

Abstract

LLM Agent Memory

Explore similar work

AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agents

LeanMem: Simple and Efficient Long-Term Memory for LLM Agents

TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents