Mnemon: Raw Records, Fast Judgments, Slow Thoughts

Guangren Wang

cs.CLSep 28, 2026

Mnemon: Raw Records, Fast Judgments, Slow Thoughts

Authors: Guangren Wang

Abstract

Long-term memory lets an LLM assistant use a history it can no longer reread, and most memory systems build it by rewriting conversations into facts, graphs or typed memories at write time. We argue that the work of memory divides, as thinking does, into two systems. Most of it is fast System 1 work: many small, independent yes/no judgments about records, such as whether a record is needed or no longer current, which a decision model makes by the dozen in a third of a second. Only a little is slow System 2 work: writing a few search queries, naming what the reply needs and composing the answer, which an LLM does well but slowly. We present Mnemon, a memory agent built on this division. It keeps conversations as raw, dated records; an LLM (System 2) plans searches over them, a decision model, Jev (System 1), judges what the searches return, and rules with explicit budgets turn the judgments into a small View for an unchanged answering model. A background pass consolidates each record once into topic timelines, value histories and standing instructions linked to the records, so that questions about a whole conversation reach evidence their own searches miss. Because nothing is decided about a record when it is written, the same agent can read any store that returns dated records. With gpt-4.1-mini answering, as in a public re-evaluation of 14 systems, Mnemon scores 91.7% on LoCoMo, the highest among them, and 83.8% on LongMemEval-S, from under 4k tokens of context per question, with the lowest effective cost index on LoCoMo. With a reasoning model answering, it reaches 92.2% on LoCoMo and 94.4% on LongMemEval-S, the latter on par with the best published results. From 100K to 10M tokens of history on BEAM, its cost per question grows by a factor of 1.11. On the same records, Jev separates gold evidence better than two LLMs and is 3-11 times faster.

Figures & tables

	LoCoMo (1,540 questions)			LongMemEval-S (500 questions)
	accuracy	context	ECI	accuracy	context	ECI
system	(%)	(k tokens)		(%)	(k tokens)
Mnemon	91.7	$3.8$	0.259	$83.8$	$3.8$	$0.198$
MemOS	$88.83$	$5.4$	$0.362$	89.2	$4.2$	0.147
Cognee	$83.48$	$32.5$	$1.670$	$51.8$	$10.3$	$0.580$
EverMemOS	$82.75$	$8.6$	$0.569$	$80.4$	$12.4$	$0.314$

Table 1: Mnemon and the 14 systems re-evaluated by OmniMemEval [ 33 ] , all with gpt-4.1-mini answering: accuracy, context sent to the answering model per question, and effective cost index (ECI, Equation 2 ; lower is better). OmniMemEval grades with gpt-4o-mini and we with gpt-4.1-mini; with DeepSeek as grader, Mnemon scores 91.4% and 85.4%. Best per column in bold.

		gpt-4.1-mini answering			reasoning
question type	questions	Mnemon	MemOS	EverMemOS	Mnemon
LoCoMo
single-hop	841	94.6	$92.51$	$86.8$	$96.1$
multi-hop	282	91.8	$88.65$	$77.78$	$92.2$
temporal	321	91.3	$85.05$	$84.11$	$92.2$
open-domain	96	$66.7$	69.79	$57.29$	$67.7$

Table 2: Accuracy (%) by question type. Mnemon is graded by gpt-4.1-mini in the standard setting (gpt-4.1-mini as System 2) and the reasoning setting (DeepSeek-V4.1-Flash); MemOS and EverMemOS, the strongest systems OmniMemEval re-evaluated, as it reports them (gpt-4.1-mini answering, gpt-4o-mini grading). Bold: best of the three systems with gpt-4.1-mini answering.

project	LoCoMo	LongMemEval-S	answering model / grader	method
Mnemon	$95.3$ †	$94.4$	DeepSeek-V4.1-Flash (thinking) / DeepSeek	raw records and a consolidated index, LLM-planned search, Jev judging
Zep / Graphiti [ 60 ]	$94.7$	$90.2$	gpt-5.4 (medium reasoning) / gpt-5.4	temporal knowledge graph + reranking
EverMemOS [ 16 ]	$93.05$	$83.0$	gpt-4.1-mini / three graders averaged	MemCell to MemScene
Mem0 [ 30 ]	$92.5$	$94.4$	gpt-5 / gpt-5	LLM-extracted facts, top 200 (about 7k tokens)
memU [ 35 ]	$92.09$	–	not stated (early version)	–
Hindsight [ 47 , 21 ]	$92.0$	$94.6$	not stated (paper: gemini-3-pro 89.6 / 91.4)	four memory networks, 36–44k tokens of context

Table 3: Each open-source project’s best published result, with whatever answering model, grader and protocol it used (checked September 26–29, 2026). The settings differ widely, so the table ranks claims, not systems. † On the revised LoCoMo labels ( Section 6.1 ); 92.2 on the original labels, which every other entry uses. ‡ Including the adversarial category.

	score, grader			context	cost ($)		median question
benchmark	gpt-4.1-mini	DeepSeek	rank	(k tokens)	/1k q.	/history	Jev calls (waves)	searches	search (ms)
LoCoMo	$91.7$	$91.4$	1/15	$3.8$	$3.27$	$0.013$	5 (4)	$7$	$14$
LongMemEval-S	$83.8$	$85.4$	2/13	$3.8$	$3.33$	$0.017$	5 (5)	$7$	$14$
HaluMem	$73.3$	$65.8$	8/13	$3.4$	$3.60$	$0.089$	7 (6)	$10$	$18$
BEAM-100K	$64.5$	$60.5$	10/12	$3.8$	$4.80$	$0.012$	9 (7)	$13$	$17$
BEAM-10M	$51.2$	$48.8$	10/12	$3.8$	$5.32$	$1.62$	10 (7)	$14$	$248$

Table 4: Mnemon on each benchmark and tier with gpt-4.1-mini answering: score under each grader (accuracy; HaluMem: share correct; BEAM: rubric score), rank among the systems OmniMemEval re-evaluated, context and cost per question, one-time consolidation cost per history, and the median question’s Jev calls (sequential waves) and searches, with the warm latency of one search on the largest history.

Explore similar work

Jul 17, 2026cs.AI

LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory

Long-term memory enables LLM agents to leverage past interactions, but dialogue histories quickly exceed the context window, forcing agents to retrieve relevant subsets at query time. Because useful evidence is sparse and scattered across verbose conversations, retrieval faces a fundamental tension: broadening recall improves coverage but floods downstream reasoning with noise, while compressing memories at write time eases retrieval but irreversibly discards details that future queries may need. We introduce LazyMem, which resolves this tension by deferring all memory construction to query time. Given a retrieved candidate pool, a lightweight model processes it in overlapping parallel windows, selectively retaining and compressing only query-relevant content. The model is trained with supervised fine-tuning followed by reinforcement learning, using a reward that jointly encourages the identification of relevant messages and the generation of compressions that are faithful to the source and useful for answering the query. On LongMemEval, LazyMem-4B achieves an LLM-judge accuracy of 0.85, outperforming the strongest non-oracle baseline while using only 213 answer-context memory tokens, 21.0 times fewer than the baseline. It further generalizes to LoCoMo without target-domain training and reduces mean latency relative to the prior query-time baseline. Code is available at https://github.com/allacnobug/LazyMem.

Jing Yu, Yibo Zhao, Jiaming Zhang +1

School of Data Science and Engineering, East China Normal University

Selective

Ask PDF

Apr 20, 2026cs.CL

HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents

Long-term conversational large language model (LLM) agents require memory systems that can recover relevant evidence from historical interactions without overwhelming the answer stage with irrelevant context. However, existing memory systems, including hierarchical ones, still often rely solely on vector similarity for retrieval. It tends to produce bloated evidence sets: adding many superficially similar dialogue turns yields little additional recall, but lowers retrieval precision, increases answer-stage context cost, and makes retrieved memories harder to inspect and manage. To address this, we propose HiGMem (Hierarchical and LLM-Guided Memory System), a two-level event-turn memory system that allows LLMs to use event summaries as semantic anchors to predict which related turns are worth reading. This allows the model to inspect high-level event summaries first and then focus on a smaller set of potentially useful turns, providing a concise and reliable evidence set through reasoning, while avoiding the retrieval overhead that would be excessively high compared to vector retrieval. On the LoCoMo10 benchmark, HiGMem achieves the best F1 on four of five question categories and improves adversarial F1 from 0.54 to 0.78 over A-Mem, while retrieving an order of magnitude fewer turns. Code is publicly available at https://github.com/ZeroLoss-Lab/HiGMem.

Shuqi Cao, Jingyi He, Fei Tan

East China Normal University, Shanghai, China · Shanghai Jiao Tong University, Shanghai, China

Conversational Memory Multi-Turn Large Language Model Conversations Summarization Semantic Anchor Hierarchical

Ask PDF

Aug 4, 2026cs.AI

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

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.

Yuxin Liao, Le Wu, Min Hou +3

Hefei University of Technology

Long-Term Memory Simple

Ask PDF