Publications

117 results for AI for Code

Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
- - Yuanzhe Liu
  - Ryan Deng
  - et al.
- 2025
- NeurIPS 2025
MermaidSeqBench: An Evaluation Benchmark for LLM-to-Mermaid Sequence Diagram Generation
- - Basel Shbita
  - Farhan Ahmed
  - et al.
- 2025
- NeurIPS 2025
Learn more about our AI for Code work
When Agents go Astray: Course-Correcting SWE Agents with PRMs
- - Shubham Gandhi
  - Jason Tsay
  - et al.
- 2025
- NeurIPS 2025
Agentic AI for Simulations Workflows
- - Vadim Elisseev
  - Robert Firth
  - et al.
- 2025
- SC 2025
Multiple Schema-Conformant Declarative Code Generation
- - Mehant Kammakomati
  - Srikanth Tamilselvam
- 2025
- ASE 2025
Evaluating Program Coverage for Code-Model Training
- - Nandakishore Menon
  - Diptikalyan Saha
- 2025
- ASE 2025
Multilingual Code Explanation for Mainframe Languages
- - Kaoru Shinkawa
  - Ai Ishida
  - et al.
- 2025
- ASE 2025
Uncovering Code Insights: Leveraging GitHub Artifacts for Deeper Code Understanding
- - Ziv Nevo
  - Orna Raz
  - et al.
- 2025
- ASE 2025
Vintage Code, Modern Judges: Meta-Validation in Low Data Regimes
- - Gal Amram
  - Ora Nova Fandina
  - et al.
- 2025
- ASE 2025
Towards Enforcing Company Policy Adherence in Agentic Workflows
- - Naama Zwerdling
  - David Boaz
  - et al.
- 2025
- EMNLP 2025