验证视界：编码智能体奖励没有银弹

摘要

一种经典直觉认为，验证解决方案比生成解决方案更容易。然而对于当今的编码智能体而言，这种直觉正在被颠覆：随着基础模型推理能力不断增强、工程体系日益成熟，生成复杂的候选方案已不再是难题——而可靠地验证这些方案反而成了更具挑战性的问题。我们所能构建的任何验证器都只是人类意图的代理，而非意图本身。这使得验证面临双重困难：其一，意图本质上具有不充分指定性，导致难以忠实地检验其是否被实现；其二，在模型训练过程中，优化会扩大代理与意图之间的差距——表现为奖励破解或信号饱和。针对这一问题，我们从三个维度——可扩展性、忠实性和鲁棒性——来刻画验证信号的质量，并指出同时实现这三者才是核心挑战。我们进一步研究了四种奖励构建方式：面向通用编码任务的测试验证器、面向前端任务的评分标准验证器、面向真实世界智能体任务的用户验证器，以及面向长周期任务的自动化智能体验证器。针对不同任务类型和策略能力水平，我们对奖励设计的核心挑战以及如何更有效地利用奖励信号进行了深入分析与实验。实验表明，针对性的验证设计能够有效抑制奖励破解、提升任务完成质量，并在多个内部和公开基准上取得显著提升。这些经验共同指向一个核心观察：没有固定的奖励函数能够随着策略能力的持续提升而始终保持有效；验证必须与生成器协同进化。

English

A classical intuition holds that verifying a solution is easier than producing one. For today's coding agents, this intuition is being inverted: as foundation models develop stronger reasoning capabilities and engineering harnesses grow more sophisticated, generating complex candidate solutions is no longer difficult -- reliably verifying them has become the harder problem. Every verifier we can build is only a proxy for human intent, never the intent itself. This makes verification subject to a twofold difficulty: first, intent is underspecified by nature, making it inherently hard to faithfully check whether it has been fulfilled; second, during model training, optimization widens the gap between proxy and intent -- manifesting as reward hacking or signal saturation. To address this, we characterize the quality of verification signals along three dimensions -- scalability, faithfulness, and robustness -- and argue that achieving all three simultaneously is the central challenge. We further study four reward constructions: a test verifier for general coding tasks, a rubric verifier for frontend tasks, the user as verifier for real-world agent tasks, and an automated agent verifier for long-horizon tasks. Across different task types and policy capability levels, we conduct in-depth analysis and experiments on the core challenges of reward design and how to more effectively leverage reward signals. Experiments show that targeted verification design can effectively suppress reward hacking, improve task completion quality, and achieve significant gains across multiple internal and public benchmarks. These experiences collectively point to a core observation: no fixed reward function can remain effective as policy capability continues to grow; and verification must co-evolve with the generator.