通过迭代优化修复指令，实现高效多轮程序纠错。
Fix Initial Programs and Iteratively Refine Repair Instructions Toward Non-Elimination Multi-Turn Program Correction
- 固定初始程序，逐步优化修复指令，流程更简洁。
- 在多个基准上性能接近顶尖方法，证明有效性。
- 适合追求可解释性与稳定性的程序生成研究者。
近期大语言模型研究强调了推理计算量扩展的重要性。为此，提出了最先进的方法——散射森林搜索（SFS），采用蒙特卡洛树搜索并结合精心设计的初始种子和文本优化来实现多轮程序修正。然而，其复杂性使得难以判断哪些因素真正提升了推理性能。针对此问题，本文分析了SFS，并提出一种更简单的方案—— extsc{修复指令的迭代优化}（IRRI），即固定初始程序并迭代优化修复指令。由于结构简单，我们基于引导归纳合成（OGIS）建立了IRRI的非消除性理论保证。在多个程序生成基准上的实验表明，IRRI的推理性能可媲美当前最优方法。结果说明：即使不依赖复杂的搜索结构，仅通过高质量修复指令对初始程序进行迭代修正，也能有效提升推理表现。
原文摘要 · Abstract (English)
Recent work on large language models (LLMs) has emphasized the importance of scaling inference compute. From this perspective, the state-of-the-art method Scattered Forest Search (SFS) has been proposed, employing Monte Carlo Tree Search with carefully crafted initial seeds and textual optimization for multi-turn program correction. However, its complexity makes it unclear what factors contribute to improvements in inference performance. To address this problem, we analyze SFS and propose a simpler method, \textsc{Iterative Refinement of Repair Instructions} (IRRI), which fixes initial programs and iteratively refines repair instructions. Because of the simplicity of IRRI, we theoretically establish the non-elimination of IRRI using Oracle-Guided Inductive Synthesis (OGIS). Experiments on several program generation benchmarks suggest that IRRI achieves inference performance comparable to state-of-the-art methods. These results indicate that, even without complex search structures, refining initial programs with high-quality repair instructions alone can effectively improve inference performance.
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。