StructMem is a structure-enriched hierarchical memory system that improves temporal reasoning and multi-hop QA on LoCoMo while cutting token usage, API calls, and runtime versus prior flat or graph-based memories.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CL 4verdicts
UNVERDICTED 4representative citing papers
Memory-R1 uses PPO and GRPO to train a Memory Manager (ADD/UPDATE/DELETE/NOOP) and Answer Agent that together outperform baselines on long-context QA benchmarks after training on only 152 examples.
Mem0 improves long-term LLM conversational performance by up to 26% on LLM-as-Judge while cutting p95 latency 91% and token costs over 90% versus full-context baselines.
TiMem introduces a Temporal Memory Tree that consolidates conversational history into hierarchical persona representations, reaching 75.30% on LoCoMo and 76.88% on LongMemEval-S while cutting recalled length by 52%.
citing papers explorer
-
StructMem: Structured Memory for Long-Horizon Behavior in LLMs
StructMem is a structure-enriched hierarchical memory system that improves temporal reasoning and multi-hop QA on LoCoMo while cutting token usage, API calls, and runtime versus prior flat or graph-based memories.
-
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
Memory-R1 uses PPO and GRPO to train a Memory Manager (ADD/UPDATE/DELETE/NOOP) and Answer Agent that together outperform baselines on long-context QA benchmarks after training on only 152 examples.
-
Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
Mem0 improves long-term LLM conversational performance by up to 26% on LLM-as-Judge while cutting p95 latency 91% and token costs over 90% versus full-context baselines.
-
TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
TiMem introduces a Temporal Memory Tree that consolidates conversational history into hierarchical persona representations, reaching 75.30% on LoCoMo and 76.88% on LongMemEval-S while cutting recalled length by 52%.