MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
MemTrace is a benchmark that evaluates LLM long-term memory at the knowledge-point level along three dimensions: memory age, question type, and evidence condition. It reveals that similar pooled accuracy masks different failures, with the main bottleneck being evidence use rather than retrieval.
[2606.17328] MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
[Submitted on 15 Jun 2026]
Title:MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
View a PDF of the paper titled MemTrace: Probing What Final Accuracy Misses in Long-Term Memory, by Xianxuan Long and 5 other authors
View PDF HTML (experimental)
Abstract:LLM agents increasingly maintain long-term memory of user facts across sessions. Yet such memory is usually evaluated by aggregating accuracy over question rows or episodes. Because this approach scores question rows independently, even when several questions probe the same fact, it cannot show how that fact behaves as conditions change. We introduce MemTrace, a benchmark whose unit of measurement is the knowledge point: a single typed fact about the user, rather than an individual question. MemTrace probes each fact along three controlled dimensions: memory age, defined by how many sessions ago the fact appeared in the history; question type, covering current state, earlier state, and trajectory of change; and evidence condition, covering present, missing, and contradicted-by-false-premise settings. Evaluating 13 memory-system configurations across four paradigms, we find that similar pooled accuracy hides different failures: recovering a fact's current and earlier states does not imply tracking how it changed, and safe abstention does not imply correcting a false premise. The dominant bottleneck is evidence use, not retrieval: when systems fail, the evidence was retrievable 10 times more often than it was missing. These results suggest that improving long-term memory requires better use of reachable evidence, not simply more storage or retrieval.
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.17328 [cs.AI]
(or arXiv:2606.17328v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.17328
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Xianxuan Long [view email] [v1] Mon, 15 Jun 2026 22:21:23 UTC (804 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled MemTrace: Probing What Final Accuracy Misses in Long-Term Memory, by Xianxuan Long and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)