mlsanityData to 14 Oct 2026

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

arXiv 2608.20400 ↗First posted 5 Jul 2026cs.AI cs.CL cs.LGcited by 0

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 14 of its 20 references that are in the map. First posted on arXiv 5 Jul 2026.

Builds on

14 of 20 references.

References · 14

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  5. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  7. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  8. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  9. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  11. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  12. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 574
2 more
  1. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  2. 2023Learning to Compress Prompts with Gist Tokenscited by 390

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory
  2. 2026Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory
  3. 2026Before Reasoning Can Fail: Pre-Evidence Procedural Failures in Agentic RAG
  4. 2026RaMem: Contextual Reinstatement for Long-term Agentic Memory
  5. 2026Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding
  6. 2026VitaBench: Memory Lifecycles Beyond Retrieval
  7. 2026What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents
  8. 2026Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents