5 papers
Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding
Daniel Maninger, Leon Chemnitz, Jannis Brugger +3
Integration of web APIs is a cornerstone of modern software systems, yet writing correct web API invocation code remains challenging due to complex and evolving API specifications.…
Benchmarking Web API Integration Code Generation
Daniel Maninger, Leon Chemnitz, Amir Molzam Sharifloo +2
API integration is a cornerstone of our digital infrastructure, enabling software systems to connect and interact. However, as shown by many studies, writing or generating correct…
Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards
Erfan Aghadavoodi Jolfaei, Daniel Maninger, Abhinav Anand +2
Large language models show strong potential for automated code generation, but lack guarantees for correctness, quality, safety, and domain-specific constraints. For instance in ro…
Where Do LLMs Still Struggle? An In-Depth Analysis of Code Generation Benchmarks
Amir Molzam Sharifloo, Maedeh Heydari, Parsa Kazerooni +2
Large Language Models (LLMs) have achieved remarkable success in code generation, and the race to improve their performance has become a central focus of AI research. Benchmarks an…
Neural-Guided Equation Discovery
Jannis Brugger, Mattia Cerrato, David Richter +4
Deep learning approaches are becoming increasingly attractive for equation discovery. We show the advantages and disadvantages of using neural-guided equation discovery by giving a…