H-Mem: Hawkes-driven Adaptive Forgetting for Long-Horizon Agent Memory
Open Access
- 6 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 5235-5245
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (U2241211)
- National Natural Science Foundation of China (62572055)
- National Natural Science Foundation of China (62372342)
This publication has 12 references indexed in Scilit:
- FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory2026
- HyperMem: Hypergraph Memory for Long-Term Conversations2026
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory2025
- Effective Personalized Search With Heterogeneous Graph Based Hawkes ProcessIEEE Transactions on Big Data, 2024
- MemoryBank: Enhancing Large Language Models with Long-Term MemoryProceedings of the AAAI Conference on Artificial Intelligence, 2024
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models2024
- Hybrid computing using a neural network with dynamic external memoryNature, 2016
- Reflections of the Environment in MemoryPsychological Science, 1991
- The working set model for program behaviorCommunications of the ACM, 1968
- Memory: A contribution to experimental psychology.1913