ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents
ProgramGym is a framework for scalable training environments of long-horizon program reproduction agents. It consists of two components: Program-Env, which constructs verifiable training environments from repositories, and Program-Agent, which combines a role-isolated workflow for analysis, implementation, and review. Experiments show that ProgramGym improves performance on program reproduction tasks.
Save an API key to vote.