AI 中文总结
本文提出VALVE验证门控框架，实现长时程代码智能体无权重更新的自我进化，在超千个SWE任务上稳定提升性能，显著降低回撤并压缩技能库。
AI 中文摘要
在无需更新模型权重的情况下实现长时程智能体自我进化，对于使已部署的智能体能够积累可复用技能并随时间改进至关重要。先前的自我进化工作主要聚焦于短时程任务，而仓库级软件工程尽管是长时程适应的理想测试平台，却仍未得到探索。在此设定下，智能体需要解决一系列连续任务，导航具有不断演化的仓库的复杂依赖关系，并持久地存储和复用经验。基于文本的技能优化为此类适应提供了一种高效的非参数化方法。然而，现有方法在长期部署中常常遭受不稳定的更新、性能回撤和智能体崩溃。在本文中，我们形式化了上下文自我进化的概念，并引入了VALVE，一个用于长时程技能优化的验证门控框架。我们确立了有限收敛性，为未来任务增益和回撤提供了理论保证，并推导了在给定容差下所需的验证和评估留出规模，具有领先阶的缩放。实验上，我们的流程VALVE在跨越超过1,000个SWE任务的进化时间跨度上实现了稳定的自我改进，在三个前沿模型（GPT-5.5、Claude-4.6和MiniMax-M2.7）上平均最终和峰值增益分别为14.9和16.5个点。验证门将平均回撤减少了75%，并产生了比无门控进化紧凑11倍的技能库。我们进一步提供了广泛的消融实验，识别了对长时程技能进化最关键的設計选择。
英文摘要
Long horizon agent self-evolution without model weight updates is essential for enabling deployed agents to accumulate reusable skills and improve over time. Prior self-evolution work has focused primarily on short-horizon tasks, while repository-level software engineering remains unexplored despite being an ideal testbed for long-horizon adaptation. In this setting, agents are required to solve streams of sequential tasks, navigate complex dependencies with evolving repositories and persistently store and reuse experience. Text-based skill optimization offers an efficient, non-parametric approach for such adaptation. However, existing methods often suffer from unstable updates, performance drawdown, and agent collapse over extended deployments. In this paper, we formalize the concept of in-context self-evolution and introduce VALVE, a validated-gated framework for long-horizon skill optimization. We establish finite convergence, provide theoretical guarantees for future-task gain and drawdown, and derive the validation and evaluation holdout sizes required for a prescribed tolerance, with leading-order scaling Empirically, our pipeline, VALVE achieves stable self-improvement over evolution horizon spanning more than 1,000 SWE tasks, with average final and peak gains of $14.9$ and $16.5$ points across three frontier models (GPT-5.5, Claude-4.6 and MiniMax-M2.7). The validation gate reduces average drawdown by 75% and produces an 11x more compact skill bank than ungated evolution. We further present extensive ablations identifying the design choices most critical to long-horizon skill evolution.
