# Benchmarking Correctness and Security in Multi-Turn Code Generation

arXiv: https://arxiv.org/abs/2510.13859 · HTML: https://mlsanity.com/paper/2510.13859/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 19 of 19)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models](https://mlsanity.com/paper/2312.04724/) (2023)
- [Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following](https://mlsanity.com/paper/2410.15553/) (2024)
- [MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2401.16745/) (2024)
- [CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation](https://mlsanity.com/paper/2501.08200/) (2025)
- [BaxBench: Can LLMs Generate Correct and Secure Backends?](https://mlsanity.com/paper/2502.11844/) (2025)
- [What Makes Large Language Models Reason in (Multi-Turn) Code Generation?](https://mlsanity.com/paper/2410.08105/) (2024)
- [An Empirical Study on Usage and Perceptions of LLMs in a Software Engineering Project](https://mlsanity.com/paper/2401.16186/) (2024)
- [Gemstones: A Model Suite for Multi-Faceted Scaling Laws](https://mlsanity.com/paper/2502.06857/) (2025)
- [An Empirical Study of Static Analysis Tools for Secure Code Review](https://mlsanity.com/paper/2407.12241/) (2024)
- [The Role of Generative AI in Software Development Productivity: A Pilot Case Study](https://mlsanity.com/paper/2406.00560/) (2024)
- [LLMs' Reshaping of People, Processes, Products, and Society in Software Development: A Comprehensive Exploration with Early Adopters](https://mlsanity.com/paper/2503.05012/) (2025)

## Built on by (most cited first, 4 of 4)

- [EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions](https://mlsanity.com/paper/2605.24110/) (2026)
- [SpecPath: Testing Coding Agents Across Contract-Equivalent Specification Histories](https://mlsanity.com/paper/2608.09799/) (2026)
- [WeSCE: A Benchmark for Measuring Security Drift in LLM-Driven Code Editing](https://mlsanity.com/paper/2608.15092/) (2026)
- [Counterexamples as Feedback for Agent Self-Correction](https://mlsanity.com/paper/2609.02892/) (2026)

## Abstract (arXiv)

AI coding assistants powered by large language models (LLMs) have transformed software development, significantly boosting productivity. While existing benchmarks evaluate the correctness and security of LLM-generated code, they are typically limited to single-turn tasks that do not reflect the iterative nature of real-world development. We introduce MT-Sec, the first benchmark to systematically evaluate both correctness and security in multi-turn coding scenarios. We construct this using a synthetic data pipeline that transforms existing single-turn tasks into semantically aligned multi-turn interaction sequences, allowing reuse of original test suites while modeling the complexity of real-world coding processes. We evaluate 32 open- and closed-source models, and three agent-scaffolding on MT-Sec and observe a consistent 20-27% drop in "correct and secure" outputs from single-turn to multi-turn settings -- even among state-of-the-art models. Beyond full-program generation, we also evaluate models on multi-turn code-diff generation -- an unexplored yet practically relevant setting -- and find that models perform worse here, with increased rates of functionally incorrect and insecure outputs. Finally, we find that while agent scaffoldings boost single-turn code generation performance, they are not quite as effective in multi-turn evaluations. Together, these findings highlight the need for benchmarks that jointly evaluate correctness and security in multi-turn, real-world coding workflows.