Knowing What is Missing: Efficient Conversational Memory via Explicit Evidence-Gap Tracking
cs.AI
Submitted: 2025-12-23
Updated: 2026-11-06
Comments: Accepted at NeurIPS 2026. 33 pages, 11 figures, 15 tables. Code: https://github.com/mbzuai-ai4bio/memr3
Code: https://github.com/Leagein/memr3
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generation
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
- Cartridges: Lightweight and general-purpose long context representations via self-study
- LightMem: Lightweight and Efficient Memory-Augmented Generation
- Evaluating Very Long-Term Conversational Memory of LLM Agents
- MemGPT: Towards LLMs as Operating Systems
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- SCM: Enhancing Large Language Model with Self-Controlled Memory Framework
- MIRIX: Multi-Agent Memory System for LLM-Based Agents
- Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents