7 papers
Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation
Didula Samaraweera, Anjana Supun, Srinath Perera
Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource Programming Languages~(LRPL…
A Methodology for Investigating AI Patterns Prevalence in Software Repositories
Srinath Perera, Hasinthaka Piyumal, Frank Leymann +1
As Artificial Intelligence(AI)-based applications take off, a clear understanding of AI patterns can uplift the quality of AI applications. Many AI patterns have been proposed in t…
Robust Agent Compensation (RAC): Teaching AI Agents to Compensate
Srinath Perera, Kaviru Hapuarachchi, Frank Leymann +1
We present Robust Agent Compensation (RAC), a log-based recovery paradigm (providing a safety net) implemented through an architectural extension that can be applied to most Agent…
You Don't Need Public Tests to Generate Correct Code
Kaushitha Silva, Srinath Perera
Multi-agent systems are frequently employed for autonomous code generation, demonstrating strong utility in complex algorithmic problem-solving. Recent studies tackle the difficult…
BACE: LLM-based Code Generation through Bayesian Anchored Co-Evolution of Code and Test Populations
Kaushitha Silva, Srinath Perera
Large Language Models (LLMs) have demonstrated impressive capabilities in code generation. While an interactive feedback loop can improve performance, writing effective tests is a…
ScheduleMe: Multi-Agent Calendar Assistant
Oshadha Wijerathne, Amandi Nimasha, Dushan Fernando +2
Recent advancements in LLMs have contributed to the rise of advanced conversational assistants that can assist with user needs through natural language conversation. This paper pre…