Skip to content
AI News HubLIVE
Original source2 min read

When Should LLM Agents Forget? Memory Filtering Under Query-Critical Resolver Errors

Summary

A new study shows that hard-deletion filtering in LLM memory systems can reduce downstream accuracy when resolver errors delete query-critical facts. Across three models, hard-drop shifts from gains of +0.186 to +0.230 at perfect resolution to losses of -0.176 to -0.181 at the lowest reliability. The authors recommend treating deletion as cost-sensitive: validate false-drop risk on matched data or default to label-free retention.

SourcearXiv AIAuthor: Samarth Vinayaka
When Should LLM Agents Forget? Memory Filtering Under Query-Critical Resolver Errors
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 30 Aug 2026]

Title:When Should LLM Agents Forget? Memory Filtering Under Query-Critical Resolver Errors

View a PDF of the paper titled When Should LLM Agents Forget? Memory Filtering Under Query-Critical Resolver Errors, by Samarth Vinayaka

View PDF HTML (experimental)

Abstract:LLM memory systems often delete facts classified as stale. We show that this hard-filtering step can reduce downstream accuracy when resolver errors delete query-critical facts. Across three models, a controlled sensitivity intervention moves hard-drop from gains of +0.186 to +0.230 at perfect resolution to losses of -0.176 to -0.181 at the lowest tested reliability. Paired targeted interventions show that false-drop causes significantly greater degradation than false-keep, while a non-deleting baseline can still fail when incorrect labels steer generation. On a frozen 102/102 calibration/test split, a simple deployment-matched gate reaches 0.655 accuracy versus 0.641 for always hard-drop and 0.662 for test-informed oracle selection. Global-accuracy crossovers require gold labels and are model- and task-specific diagnostics, not deployment thresholds. Deletion should instead be treated as cost-sensitive: validate query-critical false-drop risk on matched data, or default to label-free retention when such validation is unavailable.

Comments: 12 pages, 2 figures

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2611.17338 [cs.AI]

(or arXiv:2611.17338v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2611.17338

arXiv-issued DOI via DataCite

Submission history

From: Samarth Vinayaka [view email] [v1] Sun, 30 Aug 2026 21:52:39 UTC (37 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled When Should LLM Agents Forget? Memory Filtering Under Query-Critical Resolver Errors, by Samarth Vinayaka

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.AI

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

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?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Hard-drop filtering yields gains of +0.186 to +0.230 at perfect resolver reliability but losses of -0.176 to -0.181 at the lowest tested reliability.
  • Paired interventions show false-drop causes significantly greater degradation than false-keep.
  • On a frozen 102/102 calibration/test split, a deployment-matched gate reaches 0.655 accuracy versus 0.641 for always hard-drop and 0.662 for test-informed oracle selection.
  • Global-accuracy crossovers require gold labels and are model- and task-specific diagnostics, not deployment thresholds.

Highlights and analysis are generated automatically and may contain errors. Check the original source.