综述 | 长程智能体研究全景：基础、演化、框架、优化与前沿
Merged summary
TL;DR - A 149-page survey frames long-horizon agents as systems that sustain goals, state, tool use, recovery, and adaptation across extended task trajectories. It argues that reliable long-horizon behavior requires both runtime engineering and model-level optimization.
- Defines three task levels: within-context interaction, cross-context execution, and open-ended task streams requiring accumulated experience.
- Organizes runtime systems around workflows, memory, tools and protocols, orchestration, middleware, and continuous verification.
- Covers model-side techniques including long-context architectures, trajectory synthesis, fine-tuning, agent reinforcement learning, policy distillation, and self-evolution.
- Identifies effectiveness, efficiency, continual evolution, and trustworthiness as key open challenges.
Sources (1)
综述 | 长程智能体研究全景：基础、演化、框架、优化与前沿
TL;DR - A 149-page survey frames long-horizon agents as systems that sustain goals, state, tool use, recovery, and adaptation across extended task trajectories. It argues that reliable long-horizon behavior requires both runtime engineering and model-level optimization.
- Defines three task levels: within-context interaction, cross-context execution, and open-ended task streams requiring accumulated experience.
- Organizes runtime systems around workflows, memory, tools and protocols, orchestration, middleware, and continuous verification.
- Covers model-side techniques including long-context architectures, trajectory synthesis, fine-tuning, agent reinforcement learning, policy distillation, and self-evolution.
- Identifies effectiveness, efficiency, continual evolution, and trustworthiness as key open challenges.