LAGO：把专用语言代理变成可复用选项，SWE-bench 解决 58.6%
LAGO: Language Agents with Reusable Growing Options
新论文 LAGO：把成功子任务存成可复用选项库，不改权重跨任务变强，SWE-bench 上跑赢 mini-SWE-agent 和 Terminus 2。
论文提出 LAGO，把专用语言代理当作可复用的时序扩展选项：元代理从持久库检索或新建选项、分发子任务并验证结果，成功的新选项会被收录，选项库跨任务增长且不更新模型权重。在 500 道 SWE-bench Verified 任务上，冻结的 Qwen3.5-35B-A3B 同时担任元代理和子代理，单次尝试评测解决 58.6%。在固定的 150 任务子集上，用相同策略、温度、任务 ID 和官方 Docker 评测器对比，mini-SWE-agent、Terminus 2 和 LAGO 的解决率分别为 49.3%、57.3% 和 60.3%。50 任务的组件消融显示：去掉任务分解少解决 4 题，打乱复用内容少解决 2 题，去掉选项库少解决 6 题。
LAGO: Language Agents with Reusable Growing Options
Long-horizon tasks expose a weakness of monolithic tool-use loops: one agent must decompose, execute, and verify a task within a single trajectory. We introduce LAGO, which treats specialized language agents as reusable temporally extended options. A meta-agent retrieves options from a persistent library or spawns new ones, dispatches sub-tasks, verifies results, and admits successful novel options. The library grows across tasks without updating model weights. On 500 SWE-bench Verified tasks, frozen Qwen3.5-35B-A3B in both roles resolves 58.6% under single-attempt evaluation with the official Docker evaluator. On a fixed 150-task subset, we re-run mini-SWE-agent, Terminus 2, and LAGO with the same policy, temperature, task IDs, and evaluator; their resolve rates are 49.3%, 57.3%, and 60.3%, respectively. Cross-model experiments provide evidence consistent with a role for decomposition quality. A 50-task component ablation finds four fewer resolved tasks without decomposition, two fewer with shuffled reused content, and six fewer without the library. These results support reusable agent-options as a practical abstraction for task streams, while leaving component-level causality task- and model-dependent.
