7 papers
One Recipe, Many Harnesses: What Self-Evolution Encodes Across Languages and Models
Siqi Yang, Qianlan Yang, Yu-Xiong Wang +2
Self-evolving harnesses are closed-loop systems in which an agent inspects its own rollouts and edits its prompts, tools, and memory. They reliably improve coding agents in evaluat…
How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair
Ramtin Ehsani, Irene Manotas, Saurabh Pujar +2
Large Language Model (LLM)-based Automated Program Repair systems are advancing rapidly, yet their performance remains inconsistent. Even when provided with the same contextual inf…
Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action
Saurabh Pujar, Ira Ceka, Irene Manotas +3
The rise of large language models (LLMs) has led to dramatic improvements across a wide range of natural language tasks. Their performance on certain tasks can be further enhanced…
Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study
Ira Ceka, Hailie Mitchell, Saurabh Pujar +5
Automated Program Repair (APR) agents leverage Large Language Models (LLMs) to autonomously diagnose and fix software bugs through reasoning, planning, and tool use. Despite impres…
Cross-lingual Transfer in Programming Languages: An Extensive Empirical Study
Razan Baltaji, Saurabh Pujar, Louis Mandel +3
Large language models (LLMs) have achieved state-of-the-art performance in various software engineering tasks, including error detection, clone detection, and code translation, pri…
SeaView: Software Engineering Agent Visual Interface for Enhanced Workflow
Timothy Bula, Saurabh Pujar, Luca Buratti +2
Auto-regressive LLM-based software engineering (SWE) agents, henceforth SWE agents, have made tremendous progress (>60% on SWE-Bench Verified) on real-world coding challenges inclu…