-
The Code Whisperer: LLM and Graph-Based AI for Smell and Vulnerability Resolution
Authors:
Mohammad Baqar,
Raji Rustamov,
Alexander Hughes
Abstract:
Code smells and software vulnerabilities both increase maintenance cost, yet they are often handled by separate tools that miss structural context and produce noisy warnings. This paper presents The Code Whisperer, a hybrid framework that combines graph-based program analysis with large language models to detect, explain, and repair maintainability and security issues within a unified workflow. Th…
▽ More
Code smells and software vulnerabilities both increase maintenance cost, yet they are often handled by separate tools that miss structural context and produce noisy warnings. This paper presents The Code Whisperer, a hybrid framework that combines graph-based program analysis with large language models to detect, explain, and repair maintainability and security issues within a unified workflow. The method aligns Abstract Syntax Trees (ASTs), Control Flow Graphs (CFGs), Program Dependency Graphs (PDGs), and token-level code embeddings so that structural and semantic signals can be learned jointly. We evaluate the framework on multi-language datasets and compare it with rule-based analyzers and single-model baselines. The results indicate that the hybrid design improves detection performance and produces more useful repair suggestions than either graph-only or language-model-only approaches. We also examine explainability and CI/CD integration as practical requirements for adopting AI-assisted code review in everyday software engineering workflows.
△ Less
Submitted 12 April, 2026;
originally announced April 2026.
-
Adaptive Memory Crystallization for Autonomous AI Agent Learning in Dynamic Environments
Authors:
Rajat Khanda,
Mohammad Baqar,
Sambuddha Chakrabarti,
Satyasaran Changdar
Abstract:
Autonomous AI agents operating in dynamic environments face a persistent challenge: acquiring new capabilities without erasing prior knowledge. We present Adaptive Memory Crystallization (AMC), a memory architecture for progressive experience consolidation in continual reinforcement learning.
AMC is conceptually inspired by the qualitative structure of synaptic tagging and capture (STC) theory,…
▽ More
Autonomous AI agents operating in dynamic environments face a persistent challenge: acquiring new capabilities without erasing prior knowledge. We present Adaptive Memory Crystallization (AMC), a memory architecture for progressive experience consolidation in continual reinforcement learning.
AMC is conceptually inspired by the qualitative structure of synaptic tagging and capture (STC) theory, the idea that memories transition through discrete stability phases, but makes no claim to model the underlying molecular or synaptic mechanisms.
AMC models memory as a continuous crystallization process in which experiences migrate from plastic to stable states according to a multi-objective utility signal. The framework introduces a three-phase memory hierarchy (Liquid--Glass--Crystal) governed by an Itô stochastic differential equation (SDE) whose population-level behavior is captured by an explicit Fokker--Planck equation admitting a closed-form Beta stationary distribution.
We provide proofs of: (i) well-posedness and global convergence of the crystallization SDE to a unique Beta stationary distribution; (ii) exponential convergence of individual crystallization states to their fixed points, with explicit rates and variance bounds; and (iii) end-to-end Q-learning error bounds and matching memory-capacity lower bounds that link SDE parameters directly to agent performance.
Empirical evaluation on Meta-World MT50, Atari 20-game sequential learning, and MuJoCo continual locomotion consistently shows improvements in forward transfer (+34--43\% over the strongest baseline), reductions in catastrophic forgetting (67--80\%), and a 62\% decrease in memory footprint.
△ Less
Submitted 13 June, 2026; v1 submitted 2 April, 2026;
originally announced April 2026.
-
The Rise of Agentic Testing: Multi-Agent Systems for Robust Software Quality Assurance
Authors:
Saba Naqvi,
Mohammad Baqar,
Nawaz Ali Mohammad
Abstract:
Software testing has progressed toward intelligent automation, yet current AI-based test generators still suffer from static, single-shot outputs that frequently produce invalid, redundant, or non-executable tests due to the lack of execution aware feedback. This paper introduces an agentic multi-model testing framework a closed-loop, self-correcting system in which a Test Generation Agent, an Exe…
▽ More
Software testing has progressed toward intelligent automation, yet current AI-based test generators still suffer from static, single-shot outputs that frequently produce invalid, redundant, or non-executable tests due to the lack of execution aware feedback. This paper introduces an agentic multi-model testing framework a closed-loop, self-correcting system in which a Test Generation Agent, an Execution and Analysis Agent, and a Review and Optimization Agent collaboratively generate, execute, analyze, and refine tests until convergence. By using sandboxed execution, detailed failure reporting, and iterative regeneration or patching of failing tests, the framework autonomously improves test quality and expands coverage. Integrated into a CI/CD-compatible pipeline, it leverages reinforcement signals from coverage metrics and execution outcomes to guide refinement. Empirical evaluations on microservice based applications show up to a 60% reduction in invalid tests, 30% coverage improvement, and significantly reduced human effort compared to single-model baselines demonstrating that multi-agent, feedback-driven loops can evolve software testing into an autonomous, continuously learning quality assurance ecosystem for self-healing, high-reliability codebases.
△ Less
Submitted 5 January, 2026;
originally announced January 2026.
-
RAG4Tickets: AI-Powered Ticket Resolution via Retrieval-Augmented Generation on JIRA and GitHub Data
Authors:
Mohammad Baqar
Abstract:
Modern software teams frequently encounter delays in resolving recurring or related issues due to fragmented knowledge scattered across JIRA tickets, developer discussions, and GitHub pull requests (PRs). To address this challenge, we propose a Retrieval-Augmented Generation (RAG) framework that integrates Sentence-Transformers for semantic embeddings with FAISS-based vector search to deliver cont…
▽ More
Modern software teams frequently encounter delays in resolving recurring or related issues due to fragmented knowledge scattered across JIRA tickets, developer discussions, and GitHub pull requests (PRs). To address this challenge, we propose a Retrieval-Augmented Generation (RAG) framework that integrates Sentence-Transformers for semantic embeddings with FAISS-based vector search to deliver context-aware ticket resolution recommendations. The approach embeds historical JIRA tickets, user comments, and linked PR metadata to retrieve semantically similar past cases, which are then synthesized by a Large Language Model (LLM) into grounded and explainable resolution suggestions. The framework contributes a unified pipeline linking JIRA and GitHub data, an embedding and FAISS indexing strategy for heterogeneous software artifacts, and a resolution generation module guided by retrieved evidence. Experimental evaluation using precision, recall, resolution time reduction, and developer acceptance metrics shows that the proposed system significantly improves resolution accuracy, fix quality, and knowledge reuse in modern DevOps environments.
△ Less
Submitted 5 February, 2026; v1 submitted 9 October, 2025;
originally announced October 2025.
-
Breaking Barriers in Software Testing: The Power of AI-Driven Automation
Authors:
Saba Naqvi,
Mohammad Baqar
Abstract:
Software testing remains critical for ensuring reliability, yet traditional approaches are slow, costly, and prone to gaps in coverage. This paper presents an AI-driven framework that automates test case generation and validation using natural language processing (NLP), reinforcement learning (RL), and predictive models, embedded within a policy-driven trust and fairness model. The approach transl…
▽ More
Software testing remains critical for ensuring reliability, yet traditional approaches are slow, costly, and prone to gaps in coverage. This paper presents an AI-driven framework that automates test case generation and validation using natural language processing (NLP), reinforcement learning (RL), and predictive models, embedded within a policy-driven trust and fairness model. The approach translates natural language requirements into executable tests, continuously optimizes them through learning, and validates outcomes with real-time analysis while mitigating bias. Case studies demonstrate measurable gains in defect detection, reduced testing effort, and faster release cycles, showing that AI-enhanced testing improves both efficiency and reliability. By addressing integration and scalability challenges, the framework illustrates how AI can shift testing from a reactive, manual process to a proactive, adaptive system that strengthens software quality in increasingly complex environments.
△ Less
Submitted 21 August, 2025;
originally announced August 2025.
-
AI-Augmented CI/CD Pipelines: From Code Commit to Production with Autonomous Decisions
Authors:
Mohammad Baqar,
Saba Naqvi,
Rajat Khanda
Abstract:
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, choosing rollback strategies, tuning feature flags, and deciding when to promote a canary remain major sources of latency and operational toil. We propose AI-Augmented CI/CD Pipelines, where large language models (LLMs) a…
▽ More
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, choosing rollback strategies, tuning feature flags, and deciding when to promote a canary remain major sources of latency and operational toil. We propose AI-Augmented CI/CD Pipelines, where large language models (LLMs) and autonomous agents act as policy-bounded co-pilots and progressively as decision makers. We contribute: (1) a reference architecture for embedding agentic decision points into CI/CD, (2) a decision taxonomy and policy-as-code guardrail pattern, (3) a trust-tier framework for staged autonomy, (4) an evaluation methodology using DevOps Research and Assessment ( DORA) metrics and AI-specific indicators, and (5) a detailed industrial-style case study migrating a React 19 microservice to an AI-augmented pipeline. We discuss ethics, verification, auditability, and threats to validity, and chart a roadmap for verifiable autonomy in production delivery systems.
△ Less
Submitted 15 August, 2025;
originally announced August 2025.
-
Extending Group Relative Policy Optimization to Continuous Control: A Theoretical Framework for Robotic Reinforcement Learning
Authors:
Rajat Khanda,
Mohammad Baqar,
Sambuddha Chakrabarti,
Satyasaran Changdar
Abstract:
Group Relative Policy Optimization (GRPO) has shown promise in discrete action spaces by eliminating value function dependencies through group-based advantage estimation. However, its application to continuous control remains unexplored, limiting its utility in robotics where continuous actions are essential. This paper presents a theoretical framework extending GRPO to continuous control environm…
▽ More
Group Relative Policy Optimization (GRPO) has shown promise in discrete action spaces by eliminating value function dependencies through group-based advantage estimation. However, its application to continuous control remains unexplored, limiting its utility in robotics where continuous actions are essential. This paper presents a theoretical framework extending GRPO to continuous control environments, addressing challenges in high-dimensional action spaces, sparse rewards, and temporal dynamics. Our approach introduces trajectory-based policy clustering, state-aware advantage estimation, and regularized policy updates designed for robotic applications. We provide theoretical analysis of convergence properties and computational complexity, establishing a foundation for future empirical validation in robotic systems including locomotion and manipulation tasks.
△ Less
Submitted 25 July, 2025;
originally announced July 2025.
-
Self-Healing Software Systems: Lessons from Nature, Powered by AI
Authors:
Mohammad Baqar,
Rajat Khanda,
Saba Naqvi
Abstract:
As modern software systems grow in complexity and scale, their ability to autonomously detect, diagnose, and recover from failures becomes increasingly vital. Drawing inspiration from biological healing - where the human body detects damage, signals the brain, and activates targeted recovery - this paper explores the concept of self-healing software driven by artificial intelligence. We propose a…
▽ More
As modern software systems grow in complexity and scale, their ability to autonomously detect, diagnose, and recover from failures becomes increasingly vital. Drawing inspiration from biological healing - where the human body detects damage, signals the brain, and activates targeted recovery - this paper explores the concept of self-healing software driven by artificial intelligence. We propose a novel framework that mimics this biological model system observability tools serve as sensory inputs, AI models function as the cognitive core for diagnosis and repair, and healing agents apply targeted code and test modifications. By combining log analysis, static code inspection, and AI-driven generation of patches or test updates, our approach aims to reduce downtime, accelerate debugging, and enhance software resilience. We evaluate the effectiveness of this model through case studies and simulations, comparing it against traditional manual debugging and recovery workflows. This work paves the way toward intelligent, adaptive and self-reliant software systems capable of continuous healing, akin to living organisms.
△ Less
Submitted 25 April, 2025;
originally announced April 2025.
-
Hallucinations and Truth: A Comprehensive Accuracy Evaluation of RAG, LoRA and DoRA
Authors:
Mohammad Baqar,
Rajat Khanda
Abstract:
Recent advancements in Generative AI have significantly improved the efficiency and adaptability of natural language processing (NLP) systems, particularly through Retrieval-Augmented Generation (RAG), Low-Rank Adaptation (LoRA), and Weight-Decomposed Low-Rank Adaptation (DoRA). RAG integrates external knowledge to enhance factual consistency in generative outputs, while LoRA enables parameter-eff…
▽ More
Recent advancements in Generative AI have significantly improved the efficiency and adaptability of natural language processing (NLP) systems, particularly through Retrieval-Augmented Generation (RAG), Low-Rank Adaptation (LoRA), and Weight-Decomposed Low-Rank Adaptation (DoRA). RAG integrates external knowledge to enhance factual consistency in generative outputs, while LoRA enables parameter-efficient fine-tuning of large language models (LLMs). DoRA further refines this process by optimizing fine-tuning through adaptive parameter ranking and domain-aware weight adjustments, improving learning efficiency while maintaining inference performance.
This paper presents a large-scale empirical evaluation of RAG, LoRA, and DoRA, with model fine-tuning and generation performance assessed on 20,000 FAQ-based queries, while the knowledge base spans 400,000 entries. The study analyzes key performance metrics such as accuracy, relevance, and inference latency. Experimental results demonstrate that DoRA achieves the highest accuracy (90.1%), relevance score (0.88), and lowest latency (110 ms per query), outperforming both LoRA and RAG in real-world, domain-specific generative AI applications.
Furthermore, this study examines the trade-offs between fine-tuning efficiency, computational cost, and real-time adaptability across different models. Findings highlight RAG's effectiveness in knowledge grounding, LoRA's cost-efficient domain adaptation, and DoRA's ability to balance fine-tuning efficiency with model precision. These insights provide practical guidance for deploying AI-driven generative systems in accuracy-critical domains such as healthcare, finance, and legal services, ensuring scalability, reliability, and optimal performance in dynamic environments.
△ Less
Submitted 29 July, 2026; v1 submitted 14 February, 2025;
originally announced February 2025.
-
The Future of Software Testing: AI-Powered Test Case Generation and Validation
Authors:
Mohammad Baqar,
Rajat Khanda
Abstract:
Software testing is a crucial phase in the software development lifecycle (SDLC), ensuring that products meet necessary functional, performance, and quality benchmarks before release. Despite advancements in automation, traditional methods of generating and validating test cases still face significant challenges, including prolonged timelines, human error, incomplete test coverage, and high costs…
▽ More
Software testing is a crucial phase in the software development lifecycle (SDLC), ensuring that products meet necessary functional, performance, and quality benchmarks before release. Despite advancements in automation, traditional methods of generating and validating test cases still face significant challenges, including prolonged timelines, human error, incomplete test coverage, and high costs of manual intervention. These limitations often lead to delayed product launches and undetected defects that compromise software quality and user satisfaction. The integration of artificial intelligence (AI) into software testing presents a promising solution to these persistent challenges. AI-driven testing methods automate the creation of comprehensive test cases, dynamically adapt to changes, and leverage machine learning to identify high-risk areas in the codebase. This approach enhances regression testing efficiency while expanding overall test coverage. Furthermore, AI-powered tools enable continuous testing and self-healing test cases, significantly reducing manual oversight and accelerating feedback loops, ultimately leading to faster and more reliable software releases. This paper explores the transformative potential of AI in improving test case generation and validation, focusing on its ability to enhance efficiency, accuracy, and scalability in testing processes. It also addresses key challenges associated with adapting AI for testing, including the need for high quality training data, ensuring model transparency, and maintaining a balance between automation and human oversight. Through case studies and examples of real-world applications, this paper illustrates how AI can significantly enhance testing efficiency across both legacy and modern software systems.
△ Less
Submitted 6 March, 2026; v1 submitted 9 September, 2024;
originally announced September 2024.
-
Balancing Innovation and Ethics in AI-Driven Software Development
Authors:
Mohammad Baqar
Abstract:
This paper critically examines the ethical implications of integrating AI tools like GitHub Copilot and ChatGPT into the software development process. It explores issues such as code ownership, bias, accountability, privacy, and the potential impact on the job market. While these AI tools offer significant benefits in terms of productivity and efficiency, they also introduce complex ethical challe…
▽ More
This paper critically examines the ethical implications of integrating AI tools like GitHub Copilot and ChatGPT into the software development process. It explores issues such as code ownership, bias, accountability, privacy, and the potential impact on the job market. While these AI tools offer significant benefits in terms of productivity and efficiency, they also introduce complex ethical challenges. The paper argues that addressing these challenges is essential to ensuring that AI's integration into software development is both responsible and beneficial to society
△ Less
Submitted 10 August, 2024;
originally announced August 2024.
-
Design and Implementation of a DTMF Based Pick and Place Robotic Arm
Authors:
Muhammad Hassan,
Mohtashim Baqar
Abstract:
In recent times, developments in field of communication and robotics has progressed with leaps and bounds. In addition, the blend of both disciplines has contributed heavily in making human life easier and better. So in this work while making use of both the aforementioned technologies, a procedure for design and implementation of a mobile operated mechanical arm is proposed, that is, the proposed…
▽ More
In recent times, developments in field of communication and robotics has progressed with leaps and bounds. In addition, the blend of both disciplines has contributed heavily in making human life easier and better. So in this work while making use of both the aforementioned technologies, a procedure for design and implementation of a mobile operated mechanical arm is proposed, that is, the proposed arm will be operated via a cellular device that connects with the receiver mounted on the robotic arm. Moreover, over the duration of a call, if any key is pressed from the cellular device than an indicator indistinct to the key pressed is noticed at the receiver side. This tone represents superimposition of two distinct frequencies and referred to as DTMF (dual tone multi-frequency). Further, the mechanical arm is handled via the DTMF tone. Also, the acquired tone at the receiver is taken into a micro-controller (ATMEGA16) using the DTMF decipher module i.e. MT8870. Further, the decipher module unwinds the DTMF signal into its corresponding two bit representation and then the matched number is transmitted to the micro-controller. The micro-controller is programmed to take an action based on the decoded value. Further, the micro-controller forwards control signals to the motor driver unit to move the arm in forward/backward or multi-directional course. Lastly, the mechanical arm is capable of picking and placing objects while being controlled wirelessly over GSM (Global System for Mobile Communications).
△ Less
Submitted 9 April, 2020;
originally announced April 2020.
-
Brain Interface Based Wheel Chair Control System for Handicap -- An advance and viable approach
Authors:
Mohtashim Baqar,
Azfar Ghani,
Azeem Aftab,
Shahzad Karim Khawar
Abstract:
This paper presents advancement towards making an efficient and viable wheel chair control system based on brain computer interface via electro-oculogram (EOG) signals. The system utilizes the movement of eye as the element of purpose for controlling the movement of the wheel chair. Skin-surface electrodes are placed over skin for the purpose of acquiring the electro-oculogram signal and with the…
▽ More
This paper presents advancement towards making an efficient and viable wheel chair control system based on brain computer interface via electro-oculogram (EOG) signals. The system utilizes the movement of eye as the element of purpose for controlling the movement of the wheel chair. Skin-surface electrodes are placed over skin for the purpose of acquiring the electro-oculogram signal and with the help of differential amplifier the bio-potential is measured between the reference and the point of interest, afterwards these obtained low voltage pulses are amplified, then passed through a sallen-key filter for noise removal and smoothening. These pulses are then collected on to the micro-controller; based on these pulses motor is switched to move in either right or left direction. A prototype system was developed and tested. The system showed promising results. The test conducted showed 99.5% efficiency of movement in correct direction.
△ Less
Submitted 9 April, 2020;
originally announced April 2020.
-
Adopting E-commerce to User's Needs
Authors:
Mohammad Alshehri,
Hamza Aldabbas,
James Sawle,
Mai Abu Baqar
Abstract:
The objectives of this paper are to identify and analyse the extent to which the site is fulfilling all the user's requirements and needs. The related works comprise the history of interactive design and the benefits of user-centered development, which is the methodology followed in this survey. Moreover, there is a brief comparison between Waterfall and User-centered methodology in terms of addre…
▽ More
The objectives of this paper are to identify and analyse the extent to which the site is fulfilling all the user's requirements and needs. The related works comprise the history of interactive design and the benefits of user-centered development, which is the methodology followed in this survey. Moreover, there is a brief comparison between Waterfall and User-centered methodology in terms of addressing the issues of time saving and addressing fulfilment of users' needs. The data required to conduct this study was acquired using two research methods; the questionnaire and direct user observation, in order to address all the performance related attributes in the usability stage of the evaluation. An evaluation of the website, based on statements of usability goals and criteria, was undertaken in relation to the implementation and testing of the new design. JARIR bookstore website was chosen as a case study in this paper to investigate the usability and interactivity of the website design. The analysis section includes needs, users and tasks and data analysis, whereas the design phase covers the user interface and database design. At the end of this paper, some recommendations are presented regarding JARIR website that can be taken into account when developing the website in the future.
△ Less
Submitted 16 March, 2012;
originally announced March 2012.