竞争编程开发者终于有了一个能可靠迭代的 AI 助手——A-ProS 通过多模型反馈将 GPT-5 的初始通过率提升 2 倍以上，做算法竞赛或自动化代码生成的团队可以直接参考其架构设计。
A-ProS 是一个自主 AI 智能体，通过混合多模型反馈框架解决竞争编程问题，将解决方案生成与专门调试分离。它结合了 ChatGPT 生成器（GPT-4 和 GPT-5）与三个调试批评模型：Codestral-2508、Llama-3.3-70B 和 DeepSeek-R1，采用 2x3 因子设计。在 367 个 ICPC 世界总决赛（2011-2024）和 Codeforces（评级 1200-1800）问题上的评估显示，GPT-5 工作流经过三轮优化后，初始接受解决方案从 39 个提升到 85-90 个，GPT-4 从 15 个提升到 31-38 个。控制消融实验表明，有状态优化比无状态方法性能提升 8.5-10.6 个百分点，重复失败减少高达 3.5 倍。与基线智能体循环相比，A-ProS 的增益超过 2 倍，凸显了持久上下文和多模型反馈对于可靠自主程序合成的重要性。
A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback
Large Language Models (LLMs) demonstrate strong potential for automated code generation, yet their ability to iteratively refine solutions using execution feedback remains underexplored. Competitive programming offers an ideal testbed for this investigation, as it demands end-to-end algorithmic reasoning, precise implementation under strict computational constraints, and complete functional correctness with rigorous evaluation. In this paper, we present A-ProS, an autonomous AI agent that solves competitive programming problems through a hybrid multi-model feedback framework separating solution generation from specialized debugging. A-ProS combines ChatGPT-based generators (GPT-4 and GPT-5) with three debugging critics: Codestral-2508, Llama-3.3-70B, and DeepSeek-R1, under a 2 x 3 factorial design. We evaluate six workflows on 367 problems from ICPC World Finals (2011-2024) and Codeforces (rated 1200-1800). The results show that GPT-5 workflows improve from 39 initial accepted solutions to 85-90 after three refinement rounds, while GPT-4 improves from 15 to 31-38. A controlled ablation on 47 problems shows that stateful refinement outperforms stateless approaches by 8.5-10.6 percentage points and reduces repeated failures by up to 3.5x. Compared to baseline agent loops, A-ProS achieves over 2x greater gains, highlighting the importance of persistent context and multi-model feedback for reliable autonomous program synthesis.