AI 中文总结
该综述连接多个认知架构与语言智能体系统，重构机制并编码相关关系，指出现代智能体部分功能已实现，最强机会在机制耦合，存在五个剩余组合，贡献了机制目录、证据深度框架及可证伪议程。
AI 中文摘要
记忆、规划、反思和工具使用常被用作特征标签比较，掩盖了决定智能体实际运行的控制语义。本综述连接了十个历史认知架构、八个语言智能体运行时家族和四十四个关注机制的现代系统。通过状态、控制、转换、持久性、故障、学习和资源治理重构各机制，分别编码证据关系（E1 - E4）和迁移深度（D0 - D4）。现代智能体已实现自适应记忆、故障恢复等部分功能，多通过独立融合而非继承。最强机会在于机制耦合，如GraSP已结合多种功能。还存在五个剩余组合有待探索。我们贡献了独特机制目录、可审计证据深度框架及可证伪议程。
英文摘要
Memory, planning, reflection, and tool use are often compared as feature labels, obscuring the control semantics that determine how an agent actually runs. This review connects ten historical cognitive architectures, eight language-agent runtime families, and forty-two mechanism-focused modern systems. We reconstruct each mechanism through state, control, transition, persistence, failure, learning, and resource governance, then code evidence relation (E1-E4) separately from migration depth (D0-D4). The resulting landscape is uneven. Modern agents have operationalized substantial parts of adaptive memory, failure recovery, dynamic team selection, workflow search, skill induction, resource scheduling, and uncertainty-conditioned action, although often through independent convergence rather than documented inheritance. The strongest remaining opportunities lie in couplings among mechanisms. Closest-baseline screening closes one proposed gap: GraSP already combines calibrated multi-skill selection, typed compilation, verification, bounded repair, and replanning or ReAct fallback. Five residual bundles remain: activation with latency and action utility; typed impasse with isolated substates and resolution compilation; bounded content competition with broadcast and admission learning; persistent intention with reconsideration and live method authority; and uncertainty with resource allocation, interruption, and stopping. We contribute a distinctive-mechanism catalog, an auditable evidence-depth framework, and a falsifiable agenda for testing these bundles as composable runtime invariants.
Comments28 pages, 9 figures, 14 tables. Review article
