activity
20242026
collaborators

7 papers

cs.LG2026

Adaptive Memory Crystallization for Autonomous AI Agent Learning in Dynamic Environments

Rajat Khanda, Mohammad Baqar, Sambuddha Chakrabarti +1

Autonomous AI agents operating in dynamic environments face a persistent challenge: acquiring new capabilities without erasing prior knowledge. We present Adaptive Memory Crystalli…

cs.SE2026

The Future of Software Testing: AI-Powered Test Case Generation and Validation

Mohammad Baqar, Rajat Khanda

Software testing is a crucial phase in the software development lifecycle (SDLC), ensuring that products meet necessary functional, performance, and quality benchmarks before relea…

cs.SE2025

AI-Augmented CI/CD Pipelines: From Code Commit to Production with Autonomous Decisions

Mohammad Baqar, Saba Naqvi, Rajat Khanda

Modern software delivery has accelerated from quarterly releases to multiple deployments per day. While CI/CD tooling has matured, human decision points interpreting flaky tests, c…

cs.RO2025

Extending Group Relative Policy Optimization to Continuous Control: A Theoretical Framework for Robotic Reinforcement Learning

Rajat Khanda, Mohammad Baqar, Sambuddha Chakrabarti +1

Group Relative Policy Optimization (GRPO) has shown promise in discrete action spaces by eliminating value function dependencies through group-based advantage estimation. However,…

cs.SE2025

Self-Healing Software Systems: Lessons from Nature, Powered by AI

Mohammad Baqar, Rajat Khanda, Saba Naqvi

As modern software systems grow in complexity and scale, their ability to autonomously detect, diagnose, and recover from failures becomes increasingly vital. Drawing inspiration f…

cs.CL2025

Hallucinations and Truth: A Comprehensive Accuracy Evaluation of RAG, LoRA and DoRA

Mohammad Baqar, Rajat Khanda

Recent advancements in Generative AI have significantly improved the efficiency and adaptability of natural language processing (NLP) systems, particularly through Retrieval-Augmen…