# When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model

arXiv: https://arxiv.org/abs/2609.34227 · HTML: https://mlsanity.com/paper/2609.34227/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 27 of 27)

- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [SimpleMem: Efficient Lifelong Memory for LLM Agents](https://mlsanity.com/paper/2601.02553/) (2026)
- [On Memory Construction and Retrieval for Personalized Conversational Agents](https://mlsanity.com/paper/2502.05589/) (2025)
- [EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning](https://mlsanity.com/paper/2601.02163/) (2026)
- [On the Structural Memory of LLM Agents](https://mlsanity.com/paper/2412.15266/) (2024)
- [A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2511.17208/) (2025)
- [Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents](https://mlsanity.com/paper/2609.23986/) (2026)
- [Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity](https://mlsanity.com/paper/2602.03315/) (2026)
- [Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions](https://mlsanity.com/paper/2609.28613/) (2026)
- [MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval](https://mlsanity.com/paper/2605.06132/) (2026)
- [EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents](https://mlsanity.com/paper/2606.05894/) (2026)
- [SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval](https://mlsanity.com/paper/2603.15599/) (2026)
- [Same Ranking, Different Winner: How Scoring Targets Shape LLM Memory Benchmarks](https://mlsanity.com/paper/2605.24060/) (2026)
- [LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory](https://mlsanity.com/paper/2607.22690/) (2026)
- [LeanMem: Simple and Efficient Long-Term Memory for LLM Agents](https://mlsanity.com/paper/2608.03463/) (2026)
- [Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory](https://mlsanity.com/paper/2607.17545/) (2026)
- [Zero-Mem: Zero-Token Memory Operations for LLM Agents](https://mlsanity.com/paper/2607.29377/) (2026)
- [ConvMemory v2: A Recall-Preserving Top-10 Evidence Reranker for Conversational Memory Retrieval](https://mlsanity.com/paper/2606.10842/) (2026)
- [Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory](https://mlsanity.com/paper/2607.00017/) (2026)
- [The Retriever Should Remember: Experience-Amortized Reranking for Long-Term Agent Memory](https://mlsanity.com/paper/2608.22767/) (2026)
- [Fidelity Before Structure: Verbatim Chunks Beat Lossy Artifact Extraction in Long-Conversation LLM Memory](https://mlsanity.com/paper/2601.00821/) (2025)
- [Training-Free Lexical-Dense Fusion for Conversational-Memory Retrieval](https://mlsanity.com/paper/2606.04194/) (2026)

## Built on by (most cited first, 1 of 1)

- [What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects](https://mlsanity.com/paper/2610.05533/) (2026)

## Abstract (arXiv)

Does conversational memory need LLM-extracted facts, or is selecting the right raw turns enough? Published results disagree. Extraction-based systems report gains from distilled facts. Recent studies find raw history with good ranking does as well, but disagree about whether ranking matters. We ran a pre-registered study on held-out LoCoMo conversations and LongMemEval. At a tight budget on LoCoMo, raw turns selected by a single call to Jev, a typed decision model, are non-inferior to an LLM-extraction memory (one-sided 95% bound -3.0 points against a -5-point margin). Blind human grading narrows the margin but does not change the result. Raw turns cost 3,061 times less to write, and the result holds with a second answer model. Within this study, reranking's gain shrinks as the budget grows. It adds 17.4 points on LoCoMo and 9.1 on LongMemEval when three of 30 candidates are kept. At generous budgets it adds 1.5 and 1.1, and extraction systems are more accurate. This suggests why published results disagree. At matched context, Jev selects as accurately as an LLM reranker (non-inferiority bound -2.0) at a third of the latency, and more accurately than a multi-call graph traversal. Reranking lowers correct abstention. Plans, code and graded answers are released.