Google团队提出SKILL.state解决长时程智能体性能问题，准确率提升同时减少token消耗。
Google团队发表论文提出SKILL.state方法，解决长时程智能体执行效率问题。该方法通过替换历史记录为显式可变执行状态，减少累积token消耗。实验显示，在多个数据集、模型和执行环境中，任务准确率提升同时token消耗下降。该抽象架构与具体实现无关，可移植到现有技能运行时环境。
Good paper on long-horizon scalable agent skills.
Good paper on long-horizon scalable agent skills. DAIR.AI @dair_ai Great paper from Google and colleagues. It proposes an interesting approach to improve agents on long-horizon tasks. Long-running agents slow down and start poisoning their own context. Both symptoms come from the same design choice, which is keeping execution alive by appending every observation, action, and reasoning trace to a growing conversation. SKILL.state replaces that history with an explicit mutable execution state. At each step the model sees only the immutable skill specification, the current structured state, and the latest observation. Intermediate reasoning gets discarded the moment it produces a validated state update, so the prompt stops growing with the run. Across several datasets, models, and execution environments, task accuracy improves while cumulative token consumption drops. The abstraction is architecture-agnostic, so it ports into existing skill runtimes. Paper: arxiv.org/abs/2608.26263 Chat with Paper: academy.dair.ai/papers/explici… 🔗 View Quoted Tweet 💬 3 🔄 2 ❤️ 7 👀 2299 📊 4 ⚡