AlgoQuest: An Agentic AI-Powered DSA Revision System

Existing systems primarily rely on static problem-solving approaches and lack personalized guidance, adaptive learning, and real-time conceptual feedback. AlgoQuest addresses these challenges by integrating multi-agent AI architecture, adaptive learning mechanisms, and intelligent feedback generation into a unified tutoring platform. The proposed system utilizes specialized AI agents to analyze user-submitted code, identify logical errors, and generate scaffolded hints instead of direct solutions. This approach encourages independent problem-solving and improves conceptual understanding. The adaptive learning mechanism further personalizes the learning experience by dynamically adjusting difficulty levels and recommending problems according to individual performance and learning patterns. Experimental evaluation demonstrated that AlgoQuest significantly improves completion rates, reduces learner dropout, and enhances user engagement compared to conventional coding platforms. Features such as progress tracking, rewards, streaks, and achievement systems also contributed to improved motivation and consistency among learners. Overall, AlgoQuest represents a shift from static coding practice systems to intelligent and interactive tutoring platforms capable of providing personalized and scalable DSA learning experiences. The proposed system has strong potential to support students preparing for technical interviews, coding assessments, and competitive programming while improving both learning efficiency and conceptual clarity.

[1]    OpenAI, “GPT-4 Technical Report,” OpenAI Research Publication, 2023. [2]            LangChain AI, “LangGraph Documentation,” LangChain Framework Documentation, 2023. [3]     CrewAI, “CrewAI: Multi-Agent AI Orchestration Framework,” Official Documentation, 2024. [4]     T. Chen, Y. Liu, and H. Wang, “Artificial Intelligence in Personalized Learning Systems,” International Journal of Educational Technology, vol. 12, no. 3, pp. 145–158, 2023. [5]    S. Kumar and R. Sharma, “Adaptive Learning Approaches in Online Coding Platforms,” Journal of Computer Science Education, vol. 8, no. 2, pp. 77–89, 2022. [6]     P. Johnson and M. Lee, “Role of Intelligent Tutoring Systems in Programming       Education,”      IEEE Transactions on Learning Technologies, vol. 15, no. 4, pp. 410–421, 2021. [7]  R. Gupta, A. Verma, and K. Singh, “AI-Driven Feedback Generation for Coding Education,” International Conference on Artificial Intelligence and Education, pp. 210–218, 2024. [8]   W. Min, S. Jiang, and L. Liu, “User Engagement in Educational Systems,” ACM Computing Surveys, vol. 52, no. 5, pp. 1–30, 2019. [9] J. Anderson and P. Brown, “Personalized Learning Using Artificial Intelligence,” International Journal of Advanced Computer Science, vol. 10, no. 1, pp. 55–66, 2021. [10]    A. Patel and R. Singh, “Adaptive Recommendation Systems for Online Learning Platforms,” IEEE Access, vol. 11, pp. 22341–22355, 2023.