When Retrieval Fails Before It Begins: Structurally Indirect Prerequisite Eviction as a Retention Failure in Agentic Memory

Abstract:Agentic memory under a fixed budget involves two stages: retention and retrieval. Existing retrieval-centered paradigms implicitly assume necessary evidence survives eviction, but we challenge this by isolating a pre-retrieval failure mode: structurally indirect prerequisite eviction, in which upstream blocks weakly aligned with the query are discarded under budget pressure. We provide an operational definition of this failure, a reproducible deterministic benchmark, and per-seed trace diagnostics. Finally, we evaluate Dependency-aware Semantic Garbage Collection (DSGC), a one-hop graph-aware rule. In our main suite, DSGC improves full-chain retention from 0.03 to 0.90 under a lexical encoder and from 0.23 to 1.00 under a sentence encoder. Robustness checks then identify the budget and scaling regimes where the one-hop rule holds or degrades. Our released pipeline and failure postmortem support mechanistic analysis of retention before retrieval as a distinct failure boundary.

Accepted at the ICML 2026 Workshop on Failure Modes of Agentic AI (FAGEN@ICML 2026). Non-archival. Code: this https URL

Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)

arXiv:2608.20400 [cs.AI]

(or arXiv:2608.20400v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2608.20400 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

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.