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

arXiv:2609.34227 · cs.AI, cs.CL, cs.IR · Submitted 2026-09-28 · Read on arXiv

cs.AI, cs.CL, cs.IR

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/ris3abh/Engram

Terminology

• Accuracy — 21× in this paper · explained in 1 episode
• Fidelity — 13× in this paper · explained in 2 episodes
• Agent Memory — 10× in this paper · explained in 1 episode
• Benchmark — 10× in this paper · explained in 2 episodes
• Abstention — 9× in this paper · explained in 1 episode
• Benchmarking — 4× in this paper · explained in 3 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• LLM judge — 4× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 3× in this paper
• AI Agents — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes

Sources

• Fidelity Before Structure: Verbatim Chunks Beat Lossy Artifact Extraction in Long-Conversation LLM Memory
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval
• EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
• Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
• Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory
• Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory
• MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval
• EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents
• LeanMem: Simple and Efficient Long-Term Memory for LLM Agents
• SimpleMem: Efficient Lifelong Memory for LLM Agents
• Training-Free Lexical-Dense Fusion for Conversational-Memory Retrieval
• MemGPT: Towards LLMs as Operating Systems
• ConvMemory v2: A Recall-Preserving Top-10 Evidence Reranker for Conversational Memory Retrieval
• Same Ranking, Different Winner: How Scoring Targets Shape LLM Memory Benchmarks
• Zep: A Temporal Knowledge Graph Architecture for Agent Memory
• MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
• Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection