用动态演化的指令-代码数据生成框架，让大模型更懂编程指令。
Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution
- 将指令转为可参数化的函数模板，动态构建覆盖广的指令库。
- 通过蒙特卡洛树搜索与模型反馈结合，高效生成逻辑一致的代码。
- 迭代优化模型与模板库，适合提升编程任务的通用能力。
理解并遵循人类指令是大语言模型在自动编程中的关键能力。然而，大规模配对指令-代码数据的合成仍处于未充分探索阶段，尤其在确保多个约束间逻辑一致性方面极具挑战。本文提出IFCodeEvolve，一种基于演员-模式协同进化的指令跟随代码生成框架。通过将指令表示为参数化函数模式，动态实例化约束以构建覆盖广泛指令空间的库。在此基础上，采用蒙特卡洛树搜索（MCTS）采样器，利用演员模型反馈作为动态终止信号，高效导航该空间。为进一步逐步探索复杂问题，引入协同进化范式，根据采样统计结果，通过模式组合与突变迭代推进演员模型与模式库的演化。实验表明，IFCodeEvolve显著提升了基础模型性能，32B规模模型已达到商用顶级模型水平。此外，我们还贡献了IFCodeBench，一个经人工验证的综合性基准，包含完整解法与基于抽象语法树（AST）的鲁棒验证机制。
原文摘要 · Abstract (English)
Interpreting and following human instructions is a critical capability of large language models (LLMs) in automatic programming. However, synthesizing large-scale instruction-paired coding data remains largely unexplored and is particularly challenging when ensuring logical compatibility among multiple constraints. In this study, we propose IFCodeEvolve, an actor-schema co-evolution framework for instruction following coding data generation. By representing instructions as parametric function schema, we construct a library that covers the vast instruction space via dynamic constraint instantiation. Building upon this, Monte Carlo Tree Search (MCTS) sampler is applied to efficiently navigate this space, utilizing actor model feedback as a dynamic termination signal. Furthermore, to progressively explore challenging problems, we introduce a co-evolving paradigm that iteratively advances both the actor model and the schema library, via schema composition and mutation, based on sampler statistics. Empirical results demonstrate that IFCodeEvolve significantly boosts base model performance, with our 32B model achieving parity with proprietary SOTA models. Additionally, we contribute IFCodeBench, a comprehensive human-verified benchmark equipped with solutions and robust AST-based verification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。