AuthorsYanchen Wu, Tenghui Lin, Yingli Zhou et al.
TL;DR
Memory in the LLM Era uses a four-stage modular memory framework plus a new hierarchical tree–tier design to reach 38.79 F1 on LONGMEMEVAL, +1.87 over MemTree.
Read our summary here, or open the publisher PDF on the next tab.
THE PROBLEM
LLM agents face context overflow, where naive long-context prompting becomes token-intensive, high-latency, and unreliable for long-term conversations.
When LOCOMO conversations average 588.2 dialogue turns and LONGMEMEVAL histories reach about 115,000 tokens, agents fail at multi-session reasoning and temporal consistency.
HOW IT WORKS
Memory in the LLM Era centers on four modules: Information Extraction, Memory Management, Memory Storage, and Information Retrieval to cover all agent memory methods.
Think of Information Extraction and Memory Management as a cognitive front-end, while Memory Storage and Information Retrieval act like long-term disk plus an intelligent index.
This modular design lets Memory in the LLM Era mix and match components, enabling hierarchical, tree-based, and rule-driven memory behaviors beyond a plain context window.
DIAGRAM
This diagram shows how Memory in the LLM Era retrieves and injects relevant memories when a new query arrives.
DIAGRAM
This diagram shows how Memory in the LLM Era evaluates modular memory methods on LOCOMO and LONGMEMEVAL with shared settings.
PROCESS
Information Extraction
Memory in the LLM Era first applies Information Extraction, using direct archiving, summarization-based extraction, or graph-based extraction to convert messages into structured memories.
Memory Management
Then Memory in the LLM Era runs Memory Management to connect, integrate, transform, update, and filter memories, mirroring human-like consolidation and forgetting.
Memory Storage
Next Memory in the LLM Era organizes processed memories into flat or hierarchical Memory Storage using vector-based, graph-based, or tree-based structures.
Information Retrieval
Finally, Memory in the LLM Era uses Information Retrieval with lexical-based, vector-based, structure-based, or LLM-assisted retrieval to assemble context for the LLM.
KEY CONTRIBUTIONS
Unified modular framework for agent memory
Memory in the LLM Era formalizes agent memory as four components—Information Extraction, Memory Management, Memory Storage, and Information Retrieval—covering 10 methods like MemGPT, MemoryOS, and MemTree.
Comprehensive experimental study on LOCOMO and LONGMEMEVAL
Memory in the LLM Era reimplements 10 memory methods and evaluates them on LOCOMO and LONGMEMEVAL, analyzing F1, BLEU-1, token costs, context scalability, and position sensitivity.
New agent memory method with state-of-the-art performance
Memory in the LLM Era designs a new tree plus three-tier memory variant that reaches 38.79 F1 on LONGMEMEVAL and 43.87 F1 on LOCOMO with Qwen2.5-72B.
RESULTS
Overall F1 LONGMEMEVAL
38.79
+1.87 over MemTree
Overall F1 LOCOMO Qwen2.5-72B
43.87
+1.08 over MemOS
Information Extraction assistant F1
69.34
+11.55 over MemTree
Average token costs per dialogue
<450 tokens
Lower than MemTree and MemOS in Figure 10
Memory in the LLM Era is evaluated on LONGMEMEVAL and LOCOMO, which test long-term conversational memory, multi-session reasoning, and temporal reasoning. The 38.79 F1 and 43.87 F1 results show that the modular tree–tier design improves accuracy while keeping token usage low.
BENCHMARK
Memory in the LLM Era is evaluated on LONGMEMEVAL and LOCOMO, which test long-term conversational memory, multi-session reasoning, and temporal reasoning. The 38.79 F1 and 43.87 F1 results show that the modular tree–tier design improves accuracy while keeping token usage low.
BENCHMARK
Overall F1 scores comparing Memory in the LLM Era and strong baselines on LONGMEMEVAL.
BENCHMARK
Overall F1 scores comparing Memory in the LLM Era and strong baselines on LOCOMO.
KEY INSIGHT
Memory in the LLM Era shows that coarser-grained extraction, like MemoryOS segment summaries, can reduce token costs without hurting F1 on LONGMEMEVAL.
This is surprising because many assume finer-grained turn-level memories are always better, but the results show that carefully chosen granularity plus strong LLM reasoning can be more efficient.
WHY IT MATTERS
Memory in the LLM Era enables practitioners to reason about agent memory as interchangeable modules, not monolithic designs tied to a single system.
Builders can now systematically combine extraction, management, storage, and retrieval choices—like tree indices with three-tier storage—to design memory-augmented agents tuned for accuracy, cost, and robustness.
Nikhil Verma
· 2026
Focus Agent adds start_focus, complete_focus, a persistent Knowledge block, and an optimized Persistent Bash plus String-Replace Editor scaffold to actively compress context during long software-engineering tasks. On five hard SWE-bench Lite instances against a Baseline ReAct agent, Focus Agent achieves 22.7% token reduction (14.9M → 11.5M) while matching 3/5 = 60% task success.
Xiaohui Zhang, Zequn Sun et al.
· 2026
ActMem transforms dialogue history into atomic facts via Memory Fact Extraction, groups them with Fact Clustering, links them through a Memory KG Construction module, and uses Counterfactual-based Retrieval and Reasoning for action-aware answers. On ActMemEval, ActMem reaches 76.52% QA accuracy with DeepSeek-V3, beating LightMem’s 63.97% by 12.55 points and NaiveRAG’s 61.54%.
Xingyu Lyu, Jianfeng He et al.
· 2026
ADAM combines Anchor extraction, Distribution estimation, Anchor selection, and Query generation to adaptively probe agent memory via an auxiliary generator and entropy based selection. On the EHRAgent benchmark with Llama2-7b-chat, ADAM reaches EQ=77 and ASR=1.00, compared to MEXTRA’s EQ=44 and ASR=0.89.
Answers use this explainer on Memory Papers.
Checking…