Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents
cs.CL
Submitted: 2026-08-15
Updated: 2026-11-04
Comments: Accepted at NeurIPS 2026, Evaluations and Datasets Track
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback
- Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
- How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
- MemOS: A Memory OS for AI System
- MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents
- Natural-Language Agent Harnesses
- Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned
- If You Want Coherence, Orchestrate a Team of Rivals: Multi-Agent Models of Organizational Intelligence
- General Agentic Memory Via Deep Research
- MemEvolve: Meta-Evolution of Agent Memory Systems
- A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
- A-MEM: Agentic Memory for LLM Agents
- LightRAG: Simple and Fast Retrieval-Augmented Generation
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
- LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning
- EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data