• Mohammed Shamsul Hoque

  Author

Artificial Intelligence (AI) has revolutionized the process of teaching English language by providing customized and adaptable learning experiences. But the vast majority of current AI-based learning systems tend to offer only reactive actions and fail to incorporate autonomous planning, consistent learning modeling, and collaborative instruction, which limits their potential in facilitating self-directed English language learning. The current research offers a novel Agentic Artificial Intelligence (AAI) approach to autonomous English learning support which utilizes a combination of intelligent educational agents in order to offer personalized instruction and assessment as well as continuous learning assistance. The proposed framework is designed according to a learner-oriented multi-agent architecture including such agents as learner profiling, learning planning, grammar, vocabulary, conversation, reading, writing evaluation, assessment, and learning analytics agents. The intelligent agents mentioned above work in collaboration in order to identify learners' features, create personalized learning paths, track learners' progress, and consistently adapt instruction through feedback. This suggested framework had better results in educational terms than the traditional approach to the usage of AI technologies. In general, there was an improvement of 95.2% in educational performance, which included 96.4% of personalization, 94.8% of effectiveness of feedback, 95.7% of learner engagement, and 93.9% of autonomous learning support. In addition, significant improvements were noted in the following areas: grammar (94.2%), vocabulary (95.1%), reading (93.7%), writing (92.8%), and speaking (91.6%). This shows that autonomous collaborative agents help in personalized learning and assessment. The suggested Agentic Artificial Intelligence framework is a good tool to implement autonomous English language learning through adaptive instructional planning, personalized feedback, and continuous learning analysis using a multi-agent environment. There is great potential for increasing learner autonomy and improving English language proficiency using this framework, which may be used to develop new intelligent language learning systems in the future.

• PDF