AI 能连续干 10 小时活，不再三分钟热度
现在的 AI 助手干长活会「掉线」:任务一复杂，它要么跑偏、要么中途放弃。这篇论文训练出一个叫 Marathoner 的模型，能连续工作 10 小时以上、调用上千次工具，直到把事办完。做法是把 GitHub 上真实的大型代码改动(一次改上千行的那种)拆成任务喂给它，再把多个任务串成更难的连环任务，最后用强化学习逼它在真实环境里跑通全程。它不是你明天就能用的产品，但「AI 能持久干活」这个能力，是通往真正自主智能的关键一步。
📄 原文摘要(英文)
Humans naturally possess the ability to work persistently toward long-term goals. Given a challenging task, humans can continuously work for months or even years to accomplish a specific objective. In this paper, we propose Marathoner, an autonomous agentic model possessing the ability of ultra-long-horizon execution. Specifically, we propose a comprehensive post-training pipeline to instill this critical capability into base model. For Ultra-Long-Horizon Task Synthesis, we leverage major release PRs containing 1000+ lines of new code from diverse GitHub repositories as the primary source for synthesizing challenging task-level data. Additionally, we introduce Multi-Task Chaining, which chains multiple generated tasks into a single more challenging task, enabling the synthesis of tasks with frontier-level difficulty. For rejection sampling finetuning, we combine strong teacher model with diverse harnesses to generate trajectories on our synthesized tasks and conduct supervised finetuning on base model with rejection sampled trajectories. For reinforcement learning, cold-started model performs real-world execution through harnesses in independent sandboxes during rollout process, effectively facilitating the acquisition of genuine ultra-long-horizon execution capability. We further propose a novel reward strategy, Later Stage Bonus Reward, which explicitly encourages model to perform meaningful maneuvers during later stages of execution. Through extensive evaluation on 5 benchmarks containing ultra-long-horizon tasks, Marathoner achieves consistent and substantial performance improvements over base model and even surpasses performance of strong proprietary model. Further analysis shows that Marathoner can consistently work for 10+ hours and conduct 1000+ tool calls on highly challenging tasks.