Neuromem: A Granular Decomposition of the Streaming Lifecycle in External Memory for LLMs

Ruicheng Zhang, Xinyi Li, Tianyi Xu, Shuhao Zhang, Xiaofei Liao, Hai Jin · Feb 15, 2026 · Citations: 0

Abstract

Most evaluations of External Memory Module assume a static setting: memory is built offline and queried at a fixed state. In practice, memory is streaming: new facts arrive continuously, insertions interleave with retrievals, and the memory state evolves while the model is serving queries. In this regime, accuracy and cost are governed by the full memory lifecycle, which encompasses the ingestion, maintenance, retrieval, and integration of information into generation. We present Neuromem, a scalable testbed that benchmarks External Memory Modules under an interleaved insertion-and-retrieval protocol and decomposes its lifecycle into five dimensions including memory data structure, normalization strategy, consolidation policy, query formulation strategy, and context integration mechanism. Using three representative datasets LOCOMO, LONGMEMEVAL, and MEMORYAGENTBENCH, Neuromem evaluates interchangeable variants within a shared serving stack, reporting token-level F1 and insertion/retrieval latency. Overall, we observe that performance typically degrades as memory grows across rounds, and time-related queries remain the most challenging category. The memory data structure largely determines the attainable quality frontier, while aggressive compression and generative integration mechanisms mostly shift cost between insertion and retrieval with limited accuracy gain.

HFEPX Relevance Assessment

This paper appears adjacent to HFEPX scope (human-feedback/eval), but does not show strong direct protocol evidence in metadata/abstract.

Eval-Fit Score

5/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Unknown
Expertise required: General
Extraction source: Persisted extraction

Evaluation Lens

Evaluation modes: Automatic Metrics
Agentic eval: None
Quality controls: Not reported
Confidence: 0.45
Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

insertion-and-retrievalLongmemevalMemoryagentbench

Reported Metrics

accuracyf1latencycost

Research Brief

Deterministic synthesis

Most evaluations of External Memory Module assume a static setting: memory is built offline and queried at a fixed state. HFEPX signals include Automatic Metrics with confidence 0.45. Updated from current HFEPX corpus.

Generated Mar 5, 2026, 3:25 AM · Grounded in abstract + metadata only

Key Takeaways

Most evaluations of External Memory Module assume a static setting: memory is built offline and queried at a fixed state.
We present Neuromem, a scalable testbed that benchmarks External Memory Modules under an interleaved insertion-and-retrieval protocol and decomposes its lifecycle into five…

Researcher Actions

Treat this as method context, then pivot to protocol-specific HFEPX hubs.
Cross-check benchmark overlap: insertion-and-retrieval, Longmemeval, Memoryagentbench.
Validate metric comparability (accuracy, f1, latency).

Caveats

Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
Low-signal flag detected: protocol relevance may be indirect.

Recommended Queries

human-eval protocol design pairwise preference data quality inter-rater agreement adjudication

Research Summary

Contribution Summary

Most evaluations of External Memory Module assume a static setting: memory is built offline and queried at a fixed state.
We present Neuromem, a scalable testbed that benchmarks External Memory Modules under an interleaved insertion-and-retrieval protocol and decomposes its lifecycle into five dimensions including memory data structure, normalization strategy,…
Using three representative datasets LOCOMO, LONGMEMEVAL, and MEMORYAGENTBENCH, Neuromem evaluates interchangeable variants within a shared serving stack, reporting token-level F1 and insertion/retrieval latency.

Why It Matters For Eval

We present Neuromem, a scalable testbed that benchmarks External Memory Modules under an interleaved insertion-and-retrieval protocol and decomposes its lifecycle into five dimensions including memory data structure, normalization strategy,…
Using three representative datasets LOCOMO, LONGMEMEVAL, and MEMORYAGENTBENCH, Neuromem evaluates interchangeable variants within a shared serving stack, reporting token-level F1 and insertion/retrieval latency.

Researcher Checklist

Gap: Human feedback protocol is explicit

No explicit human feedback protocol detected.
Pass: Evaluation mode is explicit

Detected: Automatic Metrics
Gap: Quality control reporting appears

No calibration/adjudication/IAA control explicitly detected.
Pass: Benchmark or dataset anchors are present

Detected: insertion-and-retrieval, Longmemeval, Memoryagentbench
Pass: Metric reporting is present

Detected: accuracy, f1, latency, cost

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs Category Neighbor

Citations: 0 Relevance: 6.95
- Shared arXiv category (cs.AI, cs.CL)
- Shared metric mentions
- Shared terminology (accuracy, cost, llms)
Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration Category Neighbor

Citations: 0 Relevance: 4.45
- Shared arXiv category (cs.AI, cs.CL)
- Shared metric mentions
- Shared terminology (accuracy)
Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models Category Neighbor

Citations: 0 Relevance: 4.10
- Shared arXiv category (cs.CL)
- Shared metric mentions
- Shared terminology (accuracy, cost)
Think, But Don't Overthink: Reproducing Recursive Language Models Category Neighbor

Citations: 0 Relevance: 3.75
- Shared arXiv category (cs.CL)
- Shared metric mentions
- Shared terminology (accuracy, external, llms)
Contextualized Privacy Defense for LLM Agents Category Neighbor

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.AI, cs.CL)
Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification Category Neighbor

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.AI, cs.CL)
ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation Category Neighbor

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.CL)
- Shared metric mentions
- Shared terminology (cost)
Evaluating Cross-Modal Reasoning Ability and Problem Characteristics with Multimodal Item Response Theory Category Neighbor

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.CL)
- Shared metric mentions
- Shared terminology (cost)

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote