Multi-Turn Code Generation Through Single-Step Rewards

🤗 Upvotes: 21 | cs.LG, cs.AI, cs.CL

Authors:
Arnav Kumar Jain, Gonzalo Gonzalez-Pumariega, Wayne Chen, Alexander M Rush, Wenting Zhao, Sanjiban Choudhury

Title:
Multi-Turn Code Generation Through Single-Step Rewards

Arxiv:
http://arxiv.org/abs/2502.20380v1

Abstract:
We address the problem of code generation from multi-turn execution feedback. Existing methods either generate code without feedback or use complex, hierarchical reinforcement learning to optimize multi-turn rewards. We propose a simple yet scalable approach, $\mu$Code, that solves multi-turn code generation using only single-step rewards. Our key insight is that code generation is a one-step recoverable MDP, where the correct code can be recovered from any intermediate code state in a single turn. $\mu$Code iteratively trains both a generator to provide code solutions conditioned on multi-turn execution feedback and a verifier to score the newly generated code. Experimental evaluations show that our approach achieves significant improvements over the state-of-the-art baselines. We provide analysis of the design choices of the reward models and policy, and show the efficacy of $\mu$Code at utilizing the execution feedback. Our code is available at https://github.com/portal-cornell/muCode.