The emergence of large language models and their applications as AI agents have significantly advanced state-of-the-art code generation benchmarks, transforming modern software engineering tasks. However, even with test-time computed reasoning models, these systems still struggle with complex software engineering challenges. This work introduces CURA, a code understanding and reasoning agent system enhanced with verbal process supervision (VPS), achieving a 3.65\% improvement over baseline models on challenging benchmarks like BigCodeBench. Furthermore, CURA, when paired with the o3-mini model and VPS techniques, attains state-of-the-art performance. This work represents a step forward in integrating reasoning-driven architectures with LLM-based code generation, enabling agentic reasoning for language models to solve complex software engineering tasks.
View on arXiv@article{chen2025_2503.18494,
title={ Verbal Process Supervision Elicits Better Coding Agents },
author={ Hao-Yuan Chen and Cheng-Pong Huang and Jui-Ming Yao },
journal={arXiv preprint arXiv:2503.18494},
year={ 2025 }
}