AI 中文总结
研究输出格式与模型交互对单轮编码代理性能的影响，通过多模型、多格式、多任务实验发现无普遍最优格式，有格式滥用问题，提出特定于模型的输出策略及工具设计原则并开源数据模板。
AI 中文摘要
输出格式并非中立的实现细节，它会重新排列模型排名，放大或抑制个体模型差异，并决定编码代理的成败。我们进行了一项受控单轮实验，涉及3个模型（DeepSeek V4、豆包2.0 Pro、Qwen 3.7 Max）、3种输出格式（完整文件、JSON Patch、统一差异）、6个任务和20次重复，在4个开源项目中总共运行4013次。只有一个项目（tqdm）成功率非零，其他项目多次运行成功率为零。核心发现是格式与模型存在交互作用，没有普遍最优格式。豆包在JSON Patch格式下成功率达94%，DeepSeek在统一差异格式下表现出色，Qwen对完整文件格式有偏好。此外还识别出一种独特的失败机制——格式滥用。我们提出了特定于模型的输出策略，一种将格式语义约束到代理自身本地化步骤的工具设计原则，并发布所有数据和模板以实现可重复性。
英文摘要
Output format is not a neutral implementation detail -- it can reorder model rankings, amplify or suppress individual model differences, and determine whether a coding agent succeeds or fails. We conducted a controlled single-round experiment with 3 models (DeepSeek V4, Doubao 2.0 Pro, Qwen 3.7 Max) x 3 output formats (full file, JSON Patch, unified diff) x 6 tasks x 20 repetitions, totaling 4,013 runs across 4 open-source projects. Only one project (tqdm) yielded non-zero success rates: dotenv, requests, and jsoup yielded zero successes in 2,551 runs. Our central finding is a format x model interaction with no universally optimal format. Doubao achieves 94% success with JSON Patch (Cohen's h = 1.57, p < 0.001), DeepSeek excels at unified diff (66%, h = 0.63), and Qwen shows a small but significant full-file preference (50%, h = 0.29, p < 0.05). Beyond these headline results, we identify a distinct failure mechanism -- format misuse -- where agents correctly diagnose a problem but execute it with excessive scope, most vividly when a one-line fix is applied as a full-file replacement. We propose a model-specific output strategy, a tool-design principle that constrains format semantics to the agent's own localization step, and release all data and templates for reproducibility. All experimental data are available at https://doi.org/10.5281/zenodo.21505157.
Comments16 pages, 7 tables, 3 figures
