These new IBM agents will give developers new ways to solve problems — and clear their backlog
News
Mike Murphy
AI for Code
Most enterprises rely on large volumes of aging code that are a challenge to debug, maintain, and update. At IBM Research, we’re using AI to help modernize software stacks, designing automated programming and refactoring systems to help businesses keep up with the speed of modern life.
Our work
What’s an LLM context window and why is it getting larger?
NewsKim MartineauSoftware has eaten the world. What now?
Q & AKim MartineauCOBOL programmers are getting harder to find. IBM’s code-writing AI can help
NewsKim MartineauFind and fix IT glitches before they crash the system
NewsKim MartineauContinuing the momentum of AI for Code with Project Wisdom
NewsRuchir Puri- See more of our work on AI for Code
Publications
ConCodeEval: Evaluating Large Language Models for Code Constraints in Domain-Specific Languages
- Mehant Kammakomati
- Sameer Pimparkhede
- et al.
- 2025
- ACL 2025
Codellm-Devkit: A Framework for Contextualizing Code LLMs with Program Analysis Insights
- Rahul Krishna
- Rangeet Pan
- et al.
- 2025
- FSE 2025
LlamaRestTest: Effective REST API Testing with Small Language Models
- Myeongsoo Kim
- Saurabh Sinha
- et al.
- 2025
- FSE 2025
Calibration of Large Language Models on Code Summarization
- Yuvraj Singh Virk
- Premkumar Devanbu
- et al.
- 2025
- FSE 2025
AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation
- Ali Reza Ibrahimzada
- Kaiyao Ye
- et al.
- 2025
- FSE 2025
Measuring What Matters: An Aggregate Metric for Assessing Enterprise Code Summaries
- Ashita Saxena
- Palanivel Kodeswaran
- et al.
- 2025
- FSE 2025
