提出意图编译框架，解决开放世界AI代理部署难题。
Toward a Science of Intent: Closure Gaps and Delegation Envelopes for Open-World AI Agents
- 将人类意图转化为可检查的执行绑定物，实现意图编译
- 定义闭包间隙向量与授权行动区间，量化开放世界不确定性
- 为模型部署提供可验证的基准指标，适合复杂系统设计者
现有研究将智能视为通过学习结构和测试时搜索减少求解时间，系统研究则关注计算、内存与I/O向模型状态迁移的运行时机制。然而这些视角无法解释为何强大模型在开放机构中仍难部署。本文提出意图编译：将部分指定的人类目的转化为可检查的执行绑定物。关键区分在于封闭世界求解器与开放世界代理。封闭世界中验证器基本给定；开放世界中验证需分布于语义、证据、过程与制度维度。我们形式化此残余开放性为闭包间隙向量，定义委托包络为预授权的动作空间区域，区分误闭包与欠搜索，并提出基准度量以测试闭包干预是否优于额外推理时搜索。
原文摘要 · Abstract (English)
Recent work has framed intelligence in verifiable tasks as reducing time-to-solution through learned structure and test-time search, while systems work has explored learned runtimes in which computation, memory and I/O migrate into model state. These perspectives do not explain why capable models remain difficult to deploy in open institutions. We propose intent compilation: the transformation of partially specified human purpose into inspectable artifacts that bind execution. The relevant deployment distinction is closed-world solver versus open-world agent. In closed worlds, a checker is largely given; in open worlds, verification is distributed across semantic, evidentiary, procedural and institutional dimensions. Weformalize this residual openness as a closure-gap vector, define delegation envelopes as pre-authorized regions of action space, distinguish misclosure from undersearch, and outline benchmark metrics for testing when closure interventions outperform additional inference-time search.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。