When Retrieval Fails Before It Begins: Structurally Indirect Prerequisite Eviction as a Retention Failure in Agentic Memory
Source
arxiv.org
Author
Minkyu Song
Date
Why it matters
If your AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition →'s memory runs under a token budgetA cap on how many tokens a task, session, or agent run may consume — the practical control on both cost and how long an agent will grind.Full definition →, the block it needs can be evicted before retrieval ever runs — tracking what a chunk depends on, not just how well it matches the query, recovers it.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
token budget — A cap on how many tokens a task, session, or agent run may consume — the practical control on both cost and how long an agent will grind.
articleThe Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code ContextAlexander Adkins, Teimuraz Trapaidze
articleWhen Evidence Changes: Evaluating Memory Repair and Re-reading in Language-Model AgentsWenhui Chu (University at Albany, State University of New York)
articleRENDER: Controlling Reader-Facing Evidence in LLM Memory EvaluationYuan Si, Simeng Han, Daming Li, Jialu Zhang