← Search

Shubham Gandhi

2 accepted papers

2026

Hybrid-Gym: Training Coding Agents to Generalize Across Tasks

ICML 2026poster

Coding agents are increasingly used for a wide range of real-world tasks, from adding features and documentation to creating programs from scratch. Ideally, the agent should perform well across all the diverse tasks. However, most prior work concentrates on issue solving, and such single-task traini…

Cited by 0SourceScholar
2025

An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation

EMNLP 2025

We study cost-efficient collaboration between strong and weak language models for repository-level code generation, where the weak model handles simpler tasks at lower cost, and the most challenging tasks are delegated to the strong model. While many works propose architectures for this task, few an