FLARE 基准：评估语言模型智能体在配电网馈线恢复中的表现
FLARE: Physics-Grounded Evaluation of Language-Model Agents for Feeder Restoration with Degraded Observations
把大模型智能体放进电网故障恢复的场景里测，5 个模型跑了 7 万多回合，尾部失败率很扎眼，做电力 AI 的朋友可以看看这套基准。
arXiv 论文提出 FLARE（Feeder-Level Agent Restoration Evaluation），一个面向配电网故障后馈线恢复的物理约束基准。FLARE 包含 800 个 AC 可行案例，覆盖五种观测条件，智能体需在固定运行限制下收集证据、评估开关并执行恢复操作。研究在 78,750 个回合中测试了五个指令微调模型，涵盖拓扑、分布式电源和负载变化，平均归一化 regret 在 0.082 到 0.148 之间。虽然所有模型的中位 regret 为零，但 P95 regret 高达 0.814 到 1.000，暴露出明显的失败尾部；影子回放显示 15,706 个被安全机制拒绝的动作中有 96.4% 本会造成物理违规。
FLARE: Physics-Grounded Evaluation of Language-Model Agents for Feeder Restoration with Degraded Observations
Restoring service after distribution-grid faults requires decisions from incomplete and conflicting information while respecting electrical constraints. Addressing this need, we introduce FLARE (Feeder-Level Agent Restoration Evaluation), a physics-grounded benchmark for post-isolation feeder restoration. FLARE con- tains 800 AC-feasible cases across five observation settings and allows agents to gather evidence, evaluate switches, and perform restoration actions under fixed operational limits. We evaluate five instruction-tuned models over 78,750 episodes, including topology, distributed-generation, and loading shifts. Mean normalized regret ranges from 0.082 to 0.148. Although every model has zero median regret, P95 regret ranges from 0.814 to 1.000, revealing an important failure tail. Shadow replay shows that 96.4% of 15,706 guard-rejected actions would have caused a physical violation. FLARE enables reproducible evaluation of language-model based restoration support while emphasizing the need for external safety checks.
