Novel Memory Forgetting Techniques for Autonomous AI Agents: Balancing Relevance and Efficiency

2026-04-02 · Payal Fofadiya, Sunil Tiwari arxiv

Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation. Benchmarks such as LOCOMO and LOCCO report performance degradation from 0.455 to 0.05 across stages, while MultiWOZ shows 78.2% accuracy with 6.8% false memory rate under persistent retention. This work introduces an adaptive budgeted forgetting framework that regulates memory through relevanceguided scoring and bounded optimization. The approach integrates recency, frequency, and semantic alignment to maintain stability under constrained context. Comparative analysis demonstrates improved long-horizon F1 beyond 0.583 baseline levels, higher retention consistency, and reduced false memory behavior without increasing context usage. These findings confirm that structured forgetting preserves reasoning performance while preventing unbounded memory growth in extended conversational settings.

📄 PDF Abstract BibTeX arXiv:2604.02280

Code (0)

등록된 구현이 없습니다.

Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation

2026-03-31 · Ashish Rana, Chia-Chien Hung, Qumeng Sun, Julian Martin Kunkel 외 arxiv

Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues. In contrast, memory-augmented LLM agents rely on "always-on" retr…

FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory

2026-01-26 · Lei Wei, Xiao Peng, Xu Dong, Niantao Xie 외 arxiv

Large language models deployed as autonomous agents face critical memory limitations, lacking selective forgetting mechanisms that lead to either catastrophic forgetting at context boundaries or information overload with…

Reducing Catastrophic Forgetting in Modular Neural Networks by Dynamic Information Balancing

2019-12-10 · Mohammed Amer, Tomás Maul

Lifelong learning is a very important step toward realizing robust autonomous artificial agents. Neural networks are the main engine of deep learning, which is the current state-of-the-art technique in formulating adapti…

Continual Learning Lifelong learning Reinforcement Learning

Exploration and Exploitation in Visuomotor Prediction of Autonomous Agents

2013-09-19 · Laurens Bliek

This paper discusses various techniques to let an agent learn how to predict the effects of its own actions on its sensor data autonomously, and their usefulness to apply them to visual sensors. An Extreme Learning Machi…

Prediction

Lifelong Learning of Hate Speech Classification on Social Media

2021-06-05 · NAACL 2021 4 · Jing Qian, Hong Wang, Mai ElSherief, Xifeng Yan

Existing work on automated hate speech classification assumes that the dataset is fixed and the classes are pre-defined. However, the amount of data in social media increases every day, and the hot topics changes rapidly…

Classification Lifelong learning Representation Learning