LSREP: A Longitudinal State-Replay Protocol for Evaluating Conversational Memory, with ICE v2 as an Audited Local-First Architecture
cs.AI, cs.CL, cs.IR
Submitted: 2026-09-15
Updated: 2026-09-15
Comments: 37 pages. Code and evaluation artifacts: https://github.com/Deepnar/ice. The exact system snapshot used for the reported results is preserved in the "v2-paper-eval" tagged release
Code: https://github.com/Deepnar/ice
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations
- Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
- Lost in the Middle: How Language Models Use Long Contexts
- G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
- Evaluating Very Long-Term Conversational Memory of LLM Agents
- MemGPT: Towards LLMs as Operating Systems
- Generative Agents: Interactive Simulacra of Human Behavior
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- LaMP: When Large Language Models Meet Personalization
- Large Language Models are not Fair Evaluators
- Knowledge Graph Prompting for Multi-Document Question Answering
- Beyond Goldfish Memory: Long-Term Open-Domain Conversation
- Corrective Retrieval Augmented Generation
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
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