# Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation

arXiv: https://arxiv.org/abs/2602.01187 · HTML: https://mlsanity.com/paper/2602.01187/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 33 references that are in the map.
- First posted on arXiv 1 Feb 2026.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [Is Self-Repair a Silver Bullet for Code Generation?](https://mlsanity.com/paper/2306.09896/) (2023)
- [Vulnerability Detection with Code Language Models: How Far Are We?](https://mlsanity.com/paper/2403.18624/) (2024)
- [CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software](https://mlsanity.com/paper/2107.08760/) (2021)
- [CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models](https://mlsanity.com/paper/2404.13161/) (2024)
- [Dream-Coder 7B: An Open Diffusion Language Model for Code](https://mlsanity.com/paper/2509.01142/) (2025)
- [Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues](https://mlsanity.com/paper/2307.12596/) (2023)
- [Instruction Tuning for Secure Code Generation](https://mlsanity.com/paper/2402.09497/) (2024)
- [Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair](https://mlsanity.com/paper/2309.00608/) (2023)
- [Flexible and Efficient Grammar-Constrained Decoding](https://mlsanity.com/paper/2502.05111/) (2025)
- [ReposVul: A Repository-Level High-Quality Vulnerability Dataset](https://mlsanity.com/paper/2401.13169/) (2024)
- [CodeFusion: A Pre-trained Diffusion Model for Code Generation](https://mlsanity.com/paper/2310.17680/) (2023)
- [Multi-Turn Code Generation Through Single-Step Rewards](https://mlsanity.com/paper/2502.20380/) (2025)
- [ProSec: Fortifying Code LLMs with Proactive Security Alignment](https://mlsanity.com/paper/2411.12882/) (2024)
- [EpiCoder: Encompassing Diversity and Complexity in Code Generation](https://mlsanity.com/paper/2501.04694/) (2025)
- [EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning](https://mlsanity.com/paper/2410.10209/) (2024)
- [CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models](https://mlsanity.com/paper/2302.04030/) (2023)
- [Selective Prompt Anchoring for Code Generation](https://mlsanity.com/paper/2408.09121/) (2024)
- [ROCODE: Integrating Backtracking Mechanism and Program Analysis in Large Language Models for Code Generation](https://mlsanity.com/paper/2411.07112/) (2024)
- [Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences](https://mlsanity.com/paper/2506.00419/) (2025)
- [JumpCoder: Go Beyond Autoregressive Coder via Online Modification](https://mlsanity.com/paper/2401.07870/) (2024)
- [Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework](https://mlsanity.com/paper/2510.01002/) (2025)
- [Self-Infilling Code Generation](https://mlsanity.com/paper/2311.17972/) (2023)

## Built on by (most cited first, 1 of 1)

- [Activating Latent Security Knowledge through LLM-Guided Risk Analysis for Secure Code Generation](https://mlsanity.com/paper/2606.16244/) (2026)

## Abstract (arXiv)

Large Language Model (LLM) based code generation is predominantly formulated as a strictly monotonic process, appending tokens linearly to an immutable prefix. This formulation contrasts to the cognitive process of programming, which is inherently interleaved with forward generation and on-the-fly revision. While prior works attempt to introduce revision via post-hoc agents or external static tools, they either suffer from high latency or fail to leverage the model's intrinsic semantic reasoning. In this paper, we propose Stream of Revision, a paradigm shift that elevates code generation from a monotonic stream to a dynamic, self-correcting trajectory by leveraging model's intrinsic capabilities. We introduce specific action tokens that enable the model to seamlessly backtrack and edit its own history within a single forward pass. By internalizing the revision loop, our framework Stream of Revision allows the model to activate its latent capabilities just-in-time without external dependencies. Empirical results on secure code generation show that Stream of Revision significantly reduces vulnerabilities with minimal inference overhead.