ArXiv TLDR

Muhammad Asaduzzaman

3 papers · Latest:

Software Engineering

Think Harder and Don't Overlook Your Options: Revisiting Issue-Commit Linking with LLM-Assisted Retrieval

This paper re-evaluates issue-commit linking, finding that efficient retrieval combined with traditional ML reranking outperforms LLMs for accuracy.

2605.00447
Software Engineering

RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance on Stack Overflow

RAG-Reflect is an agentic LLM framework using retrieval and reflection to predict if Stack Overflow comments trigger code edits, matching fine-tuned models.

2604.22217
Software Engineering

When LLMs Lag Behind: Knowledge Conflicts from Evolving APIs in Code Generation

LLMs struggle with evolving APIs, even with RAG, due to context-memory conflicts, requiring new benchmarks and techniques for reliable code generation.

2604.09515

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.