8 papers
CodeAssay: A Multi-Metric Benchmark with Audited Ground Truth for LLM Code Generation
Shahbaz Siddeeq, Muhammad Waseem, Umar Subhan Malhi +1
Large Language Models are increasingly evaluated for code generation using test-based benchmarks. The validity of such evaluations depends on the reliability of their references an…
Vibe Coding in Software Development: A Multivocal Literature Review
Shahbaz Siddeeq, Muhammad Waseem, Kai-Kristian Kemell +3
Vibe coding is a software development practice in which developers state intent in natural language and large language models generate code. It is often framed as one-shot promptin…
Epic-Organized vs. Requirement-Aligned Gherkin: An Empirical Evaluation of LLM-Based Acceptance Criteria Generation
Shahbaz Siddeeq, Mateen Abbasi, Jussi Rasku +4
Automated authoring of Gherkin Behavior-Driven Development (BDD) acceptance criteria remains a manual bottleneck in requirements engineering. This study investigates whether epic-o…
TDD Governance for Multi-Agent Code Generation via Prompt Engineering
Tarlan Hasanli, Shahbaz Siddeeq, Bishwash Khanal +3
Large language models (LLMs) accelerate software development but often exhibit instability, non-determinism, and weak adherence to development discipline in unconstrained workflows…
LLM-based Multi-Agent System for Intelligent Refactoring of Haskell Code
Shahbaz Siddeeq, Muhammad Waseem, Zeeshan Rasheed +7
Refactoring is a constant activity in software development and maintenance. Scale and maintain software systems are based on code refactoring. However, this process is still labor…
Distributed Approach to Haskell Based Applications Refactoring with LLMs Based Multi-Agent Systems
Shahbaz Siddeeq, Zeeshan Rasheed, Malik Abdul Sami +6
We present a large language models (LLMs) based multi-agent system to automate the refactoring of Haskell codebases. The multi-agent system consists of specialized agents performin…