The Contract Net Protocol (1980) introduced coordination through contracts in multi-agent systems. Modern agent protocols standardize connectivity and interoperability; yet, none provide formal, resource governance-normative mechanisms to bound how much agents may consume or how long they may operate. We introduce Agent Contracts, a formal framework that extends the contract metaphor from task allocation to resource-bounded execution. An Agent Contract unifies input/output specifications, multi-dimensional resource constraints, temporal boundaries, and success criteria into a coherent governance mechanism with explicit lifecycle semantics. For multi-agent coordination, we establish conservation laws ensuring delegated budgets respect parent constraints, enabling hierarchical coordination through contract delegation. Empirical validation across four experiments demonstrates 90% token reduction with 525x lower variance in iterative workflows, zero conservation violations in multi-agent delegation, and measurable quality-resource tradeoffs through contract modes. Agent Contracts provide formal foundations for predictable, auditable, and resource-bounded autonomous AI deployment.

翻译：合约网协议（1980年）通过合约机制实现了多智能体系统的协调。现代智能体协议虽已标准化连接与互操作性，但均未提供形式化的资源治理规范机制来约束智能体的资源消耗或运行时长。本文提出智能体合约这一形式化框架，将合约隐喻从任务分配扩展至资源受限执行。智能体合约将输入/输出规范、多维资源约束、时间边界及成功标准统一为具有明确生命周期语义的协调治理机制。针对多智能体协调，我们建立了守恒定律以确保委托预算遵循父级约束，通过合约委托实现分层协调。四项实验的实证验证表明：在迭代工作流中实现90%的令牌缩减与525倍的方差降低，多智能体委托中实现零守恒违规，并通过合约模式实现可量化的质量-资源权衡。智能体合约为可预测、可审计且资源受限的自主人工智能部署提供了形式化基础。