AI 中文总结
该综述梳理了截至2026年8月的智能体AI在多环境中的进展与局限，提出合理委派启发式方法，为耦合评估等制定了研究议程。
AI 中文摘要
当周围系统允许语言模型的输出改变外部状态时，它们就会成为具有重要作用的智能体。目前，这些模型能够调用工具、操作界面、委派工作、保留状态、栖身于生成的世界中，还能控制机器人或实验室设备。这类进展常被描述为迈向自主的单一进程，却混淆了模型能力、系统集成、持久性和安全权限。本批判性综述综合了截至2026年8月31日的主要研究成果和官方技术规范，依据委派权限、时间持久性和环境耦合对证据进行梳理，同时区分模型、控制层（harness）和环境。在被审查的证据中，行动-接口扩展的记录比稳健完成、恢复、授权或独立验证更具说服力。模型上下文协议（Model Context Protocol）和Agent2Agent提升了互操作性，但未建立可信赖的委派机制；多智能体组织在增加专业化的同时，也带来了成本上升和相关故障。持久模拟和世界模型支持训练与规划，但本身并未展现出智能体能力；机器人技术和自动驾驶实验室确立的是有限可行性，而非无人值守开放世界的可靠性。我们提出合理委派作为分析和规范性启发式方法，而非已观察到的规律或认证分数：仅在证据支持来源、有限权限、故障检测、安全恢复和校准人类控制的情况下，才扩大行动范围。这一框架为耦合模型-控制层评估、基于能力的权限、持久状态、跨智能体问责制和分阶段物理验证制定了研究议程。
英文摘要
Large language models become consequential agents when surrounding systems let outputs change external state. Models now call tools, operate interfaces, delegate work, retain state, inhabit generated worlds, and control robots or laboratory equipment. Such advances are often narrated as one march toward autonomy, conflating model competence, system integration, persistence, and safe authority. This critical review synthesizes primary research and official technical specifications available by 31 August 2026. We organize the evidence along delegated authority, temporal persistence, and environmental coupling, while separating model, harness, and environment. Within the evidence examined, action-interface expansion is documented more convincingly than robust completion, recovery, authorization, or independent verification. Model Context Protocol and Agent2Agent improve interoperability but do not establish trustworthy delegation; multi-agent organization adds specialization alongside cost and correlated failure. Persistent simulations and world models support training and planning but do not themselves demonstrate agency; robotics and self-driving laboratories establish bounded feasibility rather than unattended open-world reliability. We propose justified delegation as an analytical and normative heuristic, not an observed law or certified score: expand action scope only where evidence supports provenance, bounded authority, failure detection, safe recovery, and calibrated human control. This framing yields a research agenda for coupled model-harness evaluation, capability-based permissions, durable state, cross-agent accountability, and staged physical validation.
CommentsReview article. 29 pages, 1 figure, 3 tables. Literature cutoff: 31 August 2026
