EMIR$^2$: Evolution-Aware Memory with Intent-Guided Multi-Round Retrieval

Jinlan Liu; Hongliang Sun; Yong Wang; Bolin Zhang; Dinabo Sui; Dianhui Chu; Zhiying Tu

cs.AISep 26, 2026

EMIR $^2$ : Evolution-Aware Memory with Intent-Guided Multi-Round Retrieval

Authors: Jinlan Liu, Hongliang Sun, Yong Wang, Bolin Zhang, Dinabo Sui, Dianhui Chu, Zhiying Tu

Organizations: Department of Computer Science, Weihai & Qingdao Research Institute Harbin Institute of Technology Weihai, China

Abstract

Long-term memory enables large language model (LLM) agents to leverage historical interactions for future tasks. However, existing memory systems struggle to utilize continuously evolving historical information, as they often rely on static memory representations and single-round retrieval strategies, failing to track factual changes or integrate distributed evidence across long-term interactions. To address these challenges, we propose EMIR $^{2}$ , an Evolution-Aware Memory framework with Intent-Guided Multi-Round Retrieval, enabling LLM agents to maintain evolving historical knowledge and adaptively retrieve relevant evidence. Specifically, EMIR $^{2}$ constructs a State-Evolving Memory Graph (SEMG) that represents long-term memory as evolving knowledge states supported by temporal event trajectories and evidential associations. By maintaining semantic states through evidence-based updates, SEMG preserves historical evolution and enables evidence tracing under complex and conflicting scenarios. Building upon this, we introduce an intent-guided multi-round retrieval mechanism that iteratively identifies missing evidence and expands retrieval based on accumulated information. Experiments on LoCoMo and MemConflict demonstrate that EMIR $^{2}$ improves long-term memory utilization, dynamic and static conflict handling, and complex retrieval performance, achieving relative improvements of more than 12% in certain categories. These results highlight the effectiveness of jointly modeling memory evolution and adaptive evidence acquisition for long-term agent interactions.

Figures & tables

Figure 1: Illustrative examples of three types of memory conflicts in long-term interactions.

Figure 2: Overview of EMIR 2 . (a) Episodic units are organized into temporal chains while maintaining evolving semantic states to construct the SEMG. (b) The LLM controller adaptively selects retrieval actions based on the query intent and accumulated evidence until sufficient information is acquired.

Model	Method	Multi-hop	Temporal	Open Domain	Single hop	Overall
Gemini 2.5 Flash	RAG	58.16 ±0.45	49.22 ±0.15	41.67 ±0.47	69.20 ±0.05	61.30
	A-Mem ( Xu et al., 2025 )	53.54 ±0.33	49.53 ±0.44	33.33 ±0.49	61.83 ±0.10	55.97
	MemoryOS ( Kang et al., 2025 )	63.82 ±0.44	47.04 ±0.53	41.66 ±0.85	71.90 ±0.22	63.35
	LangMem ( LangChain, 2025 )	61.34 ±0.79	53.58 ±0.25	38.54 ±0.33	69.68 ±0.12	62.86
	Mem0 ( Chhikara et al., 2025 )	68.79 ±1.21	61.68 ±0.29	41.66 ±1.63	73.72 ±0.10	68.31
	MRAgent ( Ji et al., 2026 )	75.17 ±0.33	80.37 ±0.15	68.75 ±0.98	90.48 ±0.10	84.21

Table 1: LLM-Judge performance comparison of different memory methods across various LLM backbones. All values are reported as percentages. Results are averaged over three independent runs, with standard deviations reported as

\pm

values. Bold numbers indicate the best performance among all methods, while underlined numbers indicate the best performance among baseline methods.

Figure 3: Ablation study of EMIR 2 on the LoCoMo benchmark. All experiments use Gemini 2.5 Flash for memory construction and answer generation, Qwen3.5-9B for retrieval controller, and GPT-4o-mini as the LLM judge. We select the best result from the main experiments as the score for the Full model.

Method	Dynamic		Static		Conditional		Average
	AA $\uparrow$	SEH@3 $\uparrow$	AA $\uparrow$	SEH@3 $\uparrow$	AA $\uparrow$	SEH@3 $\uparrow$	AA $\uparrow$
A-Mem	0.3596	0.5205	0.2639	0.3611	0.7122	0.8111	0.4452
LangMem	0.4966	0.7842	0.1944	0.3194	0.1556	0.2012	0.2822
Letta	0.3955	0.5394	0.2223	0.4167	0.8435	0.9046	0.4871
MemOS	0.3793	0.5548	0.4375	0.5694	0.8449	0.8889	0.5539
Mem0	0.1224	0.2003	0.1944	0.2917	0.7667	0.8222	0.3612

Table 2: Conflict-aware memory evaluation on MemConflict. Bold numbers indicate the best performance among all methods, while underlined numbers indicate the best performance among baseline methods.

Panel of Figure 4 — Figure 4: Analysis of adaptive multi-round retrieval. (a) Performance changes with increasing retrieval rounds. (b) Accuracy-cost trade-off under different retrieval budgets.

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Category	Relation	Semantics
Structural	FIRST_ TIMELINE_NODE	Chain head $\rightarrow$ Earliest event Provides entry from a topic-chain head to its earliest episodic event.
Structural	TEMPORAL_NEXT	Earlier event $\rightarrow$ Later event Connects consecutive events in chronological order. It expresses temporal adjacency, not causality.
Structural	INITIAL_STATE	Chain head $\rightarrow$ Initial semantic state Provides entry to the earliest separately represented semantic state, when such a node exists.
Structural	CURRENT_STATE	Chain head $\rightarrow$ Current semantic state Provides direct access to the currently accepted semantic state of a topic chain.
Structural	SEMANTIC_NEXT	Earlier state $\rightarrow$ Successor state Connects consecutive semantic epochs in their order of evolution.
Structural	SUPPORTED_BY	Event or state $\rightarrow$ Chain head Attaches an event or semantic state to its topic chain for structural organization and navigation.

Appendix

Table 3: Complete SEMG relation taxonomy. Structural relations encode graph organization, while event and state relations capture semantic connections supported by extracted evidence. Both relation types support graph traversal and retrieval.

Category	Qwen3.5-9B	Claude Controller	MRAgent
Multi-hop	88.53	91.49	90.19
Temporal	85.25	87.54	85.34

Appendix

Table 4: Effect of retrieval controller capacity under the Claude Sonnet 4.5 backbone. All configurations of EMIR 2 are kept unchanged except for the retrieval controller. Bold numbers indicate the best performance within each category.

Category	I $\rightarrow$ C	C $\rightarrow$ I	C $\rightarrow$ C	I $\rightarrow$ I
Multi-hop	16	8	242	16
Temporal	15	8	266	32
Overall	31	16	508	48

Appendix

Table 5: Instance-level prediction transitions between the Qwen3.5-9B and Claude Sonnet 4.5 retrieval controllers, where I and C denote incorrect and correct predictions, respectively.

Category	Avg. Rounds	Decomposition Rate	Complete Gold Rate	Complete Gold
Multi-hop	Qwen3.5-9B	3.58	14.5%	43.6%
Multi-hop	Claude Sonnet 4.5	2.55	42.6%	47.5%
Temporal	Qwen3.5-9B	3.22	3.7%	88.2%
Temporal	Claude Sonnet 4.5	2.51	12.8%	91.0%

Appendix

Table 6: Retrieval behavior comparison between the Qwen3.5-9B and Claude Sonnet 4.5 controllers. Complete Gold denotes the proportion of questions for which all annotated supporting evidence is retained.

Retrieval Statistics	Full	w/o cross-rel
Graph Expansion Count	5957	5548
Candidates from Graph Expansion	3503	2800
Final Candidates from Graph Expansion	2372	1798
Final Retrieved Candidates	18083	17997

Appendix

Table 7: Retrieval behavior analysis of the full model and the w/o cross-rel variant.

Evidence Statistics	Full	w/o cross-rel
Retrieved Gold Evidence	1721	1723
Retrieved via Graph Expansion	197	101
Uniquely Retrieved Evidence	41	36

Appendix

Table 8: Analysis of evidence retrieved through cross-chain edges.

Method	Dynamic		Static		Conditional	Average
	AA	UOCS	AA	CRS	AA	AA
A-Mem	0.3596	0.2911	0.2639	0.2501	0.7122	0.4452
LangMem	0.4966	0.3579	0.1944	0.2083	0.1556	0.2822
Letta	0.3955	0.3527	0.2223	0.2031	0.8435	0.4871
MemOS	0.3793	0.3818	0.4375	0.2361	0.8449	0.5539
Mem0	0.1224	0.1130	0.1944	0.1528	0.7667	0.3612

Appendix

Table 9: Black-box performance of memory systems on MemConflict by conflict type. Bold numbers indicate the best performance among all methods, while underlined numbers indicate the best performance among baseline methods.

Method	Dynamic		Static		Conditional		Average
	SEH@3	SRS	SEH@3	SRS	SEH@3	SRS	SEH@3	SRS
A-Mem	0.5205	0.4341	0.3611	0.2854	0.8111	0.7288	0.5642	0.4828
LangMem	0.7842	0.7089	0.3194	0.2697	0.2012	0.1944	0.4349	0.3910
Letta	0.5394	0.4620	0.4167	0.3099	0.9046	0.7653	0.6202	0.5124
MemOS	0.5548	0.4552	0.5694	0.4886	0.8889	0.8198	0.6710	0.5879
Mem0	0.2003	0.1587	0.2917	0.2401	0.8222	0.7780	0.4381	0.3923

Appendix

Table 10: White-box memory retrieval and ranking of memory systems on MemConflict by conflict type. Bold numbers indicate the best performance among all methods, while underlined numbers indicate the best performance among baseline methods.

Memory Management for LLM Agents

See all 58 papers

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
Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory
Jun 9, 2026Suozhao Ji, Baodong Wu, Zehao Wang +8LLM Agent Memory Persistent Memory for Language Models
1Infinigence AI · 2Tsinghua University · 3Shanghai Jiaotong University
Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents
Sep 13, 2026Yuanyi Song, Yukai Wang, Xinbei Ma +7LLM Agent Memory Long-Term Conversational Memory
Shanghai Jiao Tong University · OPPO · National University of Singapore

Aug 4, 2026J/K move · Enter open · S save

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

Yuxin Liao, Le Wu, Min Hou, Hao Liu+2

Hefei University of Technology

LLM Agent Memory Persistent Memory for Language Models Long-Term Conversational Memory Agent Memory Management Memory Management for LLM Agents

Open paper AskPDF arXiv

Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history. However, existing memory systems typically process heterogeneous dialogue content through a uniform summarization and retrieval pipeline, leading to either excessive token consumption or irreversible loss of fine-grained evidence. We argue that historical dialogue content should be handled differently according to its compressibility, temporal dynamics, and fidelity requirements. Based on this insight, we propose LeanMem, a lightweight long-term memory framework. LeanMem first filters out low-value content, then stores informative segments as compact profile memory, temporally structured event memory, or source-grounded record memory, depending on the nature of the information. During maintenance, only dynamically evolving event memories are selectively updated, avoiding redundant consolidation of stable profiles and immutable records. During inference, LeanMem dynamically selects memory types and allocates retrieval budgets according to query-specific evidence demands, assembling relevant evidence on demand. On LoCoMo and LongMemEval-S with GPT-4.1-mini and Qwen3-8B, LeanMem improves accuracy over the strongest memory-based baseline in every setting, by up to 15.1 points, at the lowest or near-lowest construction cost, inference tokens, and latency. The code and datasets are included in the supplementary materials.

Abstract

Memory Management for LLM Agents

Explore similar work

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

Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory

Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents