Preprint · 2026 · Open access

Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA

Yufeng Li, Shuxin Li, Zhenhua Xu, Junxian Li, Peng Zeng, Sheng Yao, Changting Lin, Gaolei Li, Ran Bi, Meng Han

arXiv (Cornell University) · Published 7 October 2026 · DOI 10.48550/arxiv.2610.09348

Open PDFView at the publisherCite this paper

In brief

“Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA” is a 2026 preprint by Yufeng Li and 9 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
1
Most cited in
2026 (1)
References
13
Authors
10

Abstract

LLM agents that interact with a user across many sessions accumulate histories that exceed their context window, so they store past interactions in an external memory and answer each question from a small set of retrieved records. Existing memory systems rank records by lexical or embedding relevance, yet the top-ranked memories can each be relevant while jointly omitting a complementary fact that the answer requires, especially for multi-session and temporal questions. Drawing on the distinction between relevance and sufficiency in legal evidence scholarship, we recast memory retrieval as constructing a sufficient memory set. To operationalize this view, we introduce a blinded LLM judgment over the retrieved set, together with Gold Hit and Turn Hit as evidence-coverage proxies. We then propose Budgeted Flat Reconstruction (BFR), which builds sufficient sets over a fixed flat memory store in two stages. Specifically, we first apply Formal Concept Analysis for Memory Selection (FCA-MS) to decompose the question into information requirements and select a compact candidate subset that jointly covers them. Then, we repeatedly acquire unseen records through deeper text search or complementary entity and session views, stopping when the budget is exhausted. Experiments on LoCoMo and LongMemEval-S show that BFR outperforms same-store adaptations of recent agent-memory systems in both answer quality and evidence coverage. Specifically, on LongMemEval-S it raises judged accuracy from 72.4% to 82.2% and Turn Hit to 91.4%.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Li, Y., Li, S., Xu, Z., Li, J., Zeng, P., Yao, S., Lin, C., Li, G., Bi, R., & Han, M. (2026). Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.09348

MLA 9

Li, Yufeng, et al. “Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2610.09348.

Chicago

Li, Yufeng, Shuxin Li, Zhenhua Xu, Junxian Li, Peng Zeng, Sheng Yao, Changting Lin, Gaolei Li, Ran Bi, and Meng Han. 2026. “Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.09348.

Harvard

Li, Y. et al. (2026) ‘Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA’, arXiv (Cornell University). doi:10.48550/arxiv.2610.09348.

IEEE

Y. Li et al., “Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2610.09348.

BibTeX

@misc{li2026relevance,
  title     = {{Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA}},
  author    = {Li, Yufeng and Li, Shuxin and Xu, Zhenhua and Li, Junxian and Zeng, Peng and Yao, Sheng and Lin, Changting and Li, Gaolei and Bi, Ran and Han, Meng},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2610.09348},
  url       = {https://doi.org/10.48550/arxiv.2610.09348}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior

  • long-term memory retrieval
  • LLM agents
  • external memory
  • evidence law
  • formal concept analysis
  • memory selection
  • LoCoMo

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Li, Y., Li, S., Xu, Z., Li, J., Zeng, P., Yao, S., Lin, C., Li, G., Bi, R., & Han, M. (2026). Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.09348

How many times has this paper been cited?

1 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Yufeng Li, Shuxin Li, Zhenhua Xu, Junxian Li, Peng Zeng, Sheng Yao, Changting Lin, Gaolei Li, Ran Bi, Meng Han.

What is the DOI of this paper?

10.48550/arxiv.2610.09348, permanently at https://doi.org/10.48550/arxiv.2610.09348. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.