← Back to all news
arXiv AI By Oleeviya Babu Poikarayil, Tony Basil Babu, Abdulrahman Nahhas, Het Darshan Mehta, Jawid Ahmad Baktash, Ernesto William De Luca, Klaus Turowski

When Retrieval Is Not Enough: Obsolete Facts in Agent Memory

Read the original on arXiv AI →

The study shows that in memory‑agent benchmarks, simply retrieving the correct fact does not guarantee accurate answers. On the FactConsolidation task, increasing the evidence budget from 64 to 512 tokens caused accuracy to drop, even though the newest statement was present in every retrieved set. Experiments with Qwen models revealed that replacing an unrelated statement with an obsolete competing statement drastically reduced accuracy, indicating that outdated information can be more harmful than irrelevant evidence.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 30

Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents

The paper introduces the Distributed‑Evidence Paradox, where long‑running LLM agents compress past interactions into persistent memories that may not be fully supported by the interaction history. It defines three key requirements—evidence scope, compositional validity, and admission reliability—and proposes DerivAudit, a framework that checks whether a memory is truly supported by the available history. Experiments on two memory corpora show that expanding the evidence base can recover support for many memories, yet many remain unsupported, and broader evidence alone does not guarantee reliable admission.

By Hongjun Liu, Chen Zhao
llmsagents
More like this →