LoCoMo

LoCoMo is a dataset/benchmark used to evaluate the performance of memory-augmented LLM agents in long-horizon interactions.

Papers using LoCoMo (25)

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning2025 · 98 citesEpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory2025 · 6 citesMnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory2026MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agents2026MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents2026Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory2026MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution2026δ-mem: Efficient Online Memory for Large Language Models2026Locas: Your Models are Principled Initializers of Locally-Supported Parametric Memories2026Query-focused and Memory-aware Reranker for Long Context Processing2026EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents2026MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing2026GAM: Hierarchical Graph-based Agentic Memory for LLM Agents2026Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations2026Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agents2026Developing Adaptive Context Compression Techniques for Large Language Models (LLMs) in Long-Running Interactions2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents2026Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents2026DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs2026E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory2026MemR$^3$: Memory Retrieval via Reflective Reasoning for LLM Agents2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents2025MIRIX: Multi-Agent Memory System for LLM-Based Agents2025MemLoRA: Distilling Expert Adapters for On-Device Memory Systems2025