EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Lifelong Learning of Large Language Model Based Agents: A Roadmap

Junhao Zheng, Chengming Shi, Xidi Cai, Qiuke Li, Duzhen Zhang, Chenxing Li, Dong Yu, Qianli Ma

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-05 · 48 (5) · 5552-5571

DOI: 10.1109/tpami.2025.3650546 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-05. Verfasst von Junhao Zheng und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Artificial Intelligence, Natural Language Processing, Language, Learning. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 188 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province, Science and Technology Planning Project of Guangdong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lifelong learning, also known as continual or incremental learning, is a crucial component for advancing Artificial General Intelligence (AGI) by enabling systems to continuously adapt in dynamic environments. While large language models (LLMs) have demonstrated impressive capabilities in natural language processing, existing LLM agents are typically designed for static systems and lack the ability to adapt over time in response to new challenges. This survey is the first to systematically summarize the potential techniques for incorporating lifelong learning into LLM-based agents. We categorize the core components of these agents into three modules: the perception module for multimodal input integration, the memory module for storing and retrieving evolving knowledge, and the action module for grounded interactions with the dynamic environment. We highlight how these pillars collectively enable continuous adaptation, mitigate catastrophic forgetting, and improve long-term performance. This survey provides a roadmap for researchers and practitioners working to develop lifelong learning capabilities in LLM agents, offering insights into emerging trends, evaluation metrics, and application scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceNatural Language ProcessingLanguageLearningHumansLarge Language Models

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Guangdong Province
  • Science and Technology Planning Project of Guangdong Province
  • National Key R&D Program of China

Zitieren

APA

Zheng, J., Shi, C., Cai, X., Li, Q., Zhang, D., Li, C., Yu, D., & Ma, Q. (2026). Lifelong Learning of Large Language Model Based Agents: A Roadmap. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(5), 5552-5571. https://doi.org/10.1109/tpami.2025.3650546

Vancouver

Zheng J, Shi C, Cai X, Li Q, Zhang D, Li C, et al. Lifelong Learning of Large Language Model Based Agents: A Roadmap. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(5):5552-5571. doi:10.1109/tpami.2025.3650546

BibTeX
@article{Zheng2026,
  author = {Zheng, Junhao and Shi, Chengming and Cai, Xidi and Li, Qiuke and Zhang, Duzhen and Li, Chenxing and Yu, Dong and Ma, Qianli},
  title = {Lifelong Learning of Large Language Model Based Agents: A Roadmap},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {5},
  pages = {5552--5571},
  doi = {10.1109/tpami.2025.3650546}
}
Kostenlos starten →