# CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement

arXiv: https://arxiv.org/abs/2508.10059 · HTML: https://mlsanity.com/paper/2508.10059/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2025.

## Built on by (most cited first, 7 of 7)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search](https://mlsanity.com/paper/2512.23167/) (2025)
- [EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention](https://mlsanity.com/paper/2508.16771/) (2025)
- [ContextEvolve: Multi-Agent Context Compression for Systems Code Optimization](https://mlsanity.com/paper/2602.02597/) (2026)
- [VERITAS: Verifier-Guided Proof Search for Zero-Shot Formal Theorem Proving](https://mlsanity.com/paper/2606.19399/) (2026)
- [Quality-Driven Agentic Reasoning for LLM-Assisted Software Design: Questions-of-Thoughts (QoT) as a Time-Series Self-QA Chain](https://mlsanity.com/paper/2603.11082/) (2026)
- [SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair](https://mlsanity.com/paper/2604.17184/) (2026)

## Abstract (arXiv)

While Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, they often produce solutions that lack guarantees of correctness, robustness, and efficiency. This limitation is particularly acute in domains requiring strict constraints. CodeGrad introduces a principled framework that integrates rigorous verification techniques directly into an iterative LLM-based generation loop. It uniquely treats code as a differentiable variable, converting structured feedback and mathematical constraints into a textual pseudo-gradient. This gradient guides the model to iteratively refine solutions, ensuring they are not only functional but also robust and mathematically justified. We evaluate CodeGrad on the HumanEval, HumanEval+, and LiveCodeBench benchmarks. Our implementation outperforms strong baselines, achieving an absolute improvement of up to 27% on HumanEval and a 41% relative improvement on the challenging LiveCodeBench V6. StructuredGrad generates mathematically justified code that is robust and efficient, paving the way for reliable AI-assisted software development in high-stakes applications.