arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.28181cs.AIcs.CLcs.LG
收藏

大规模合成计算机用于长期生产力模拟

Synthetic Computers at Scale for Long-Horizon Productivity Simulation

Microsoft(微软)

Tao Ge, Baolin Peng, Hao Cheng, Jianfeng Gao

AI总结:

本文提出大规模合成计算机方法,通过生成真实文件夹结构和内容丰富的 artifacts,模拟长期生产力场景,验证了其在不同领域中的有效性。

摘要:

现实的长期生产力工作强烈依赖于用户特定的计算机环境,其中大部分工作上下文通过目录结构和内容丰富的 artifacts 存储和组织。为扩展此类生产力场景的合成数据创建,我们引入了大规模合成计算机方法,一种可扩展的方法用于创建此类环境,具有真实文件夹层次和内容丰富的 artifacts(例如文档、电子表格和演示文稿)。在每个合成计算机上,我们运行长期模拟:一个代理创建特定于计算机用户的生产力目标,需要多个专业交付成果和约一个月的人类工作;另一个代理则扮演该用户,持续在计算机上工作——例如导航文件系统以获得基础,协调与模拟合作者,以及生成专业 artifacts——直到这些目标完成。在初步实验中,我们创建了1000台合成计算机并在其上运行长期模拟;每个运行需要超过8小时的代理运行时间,平均超过2000次回合。这些模拟产生丰富的经验学习信号,其有效性通过在域内和域外生产力评估中显著改进的代理性能得到验证。鉴于人物在十亿级规模上普遍存在,这种方法原则上可以扩展到数百万甚至数十亿的合成用户世界,只要计算资源足够,从而覆盖更广泛的职业、角色、上下文、环境和生产力需求。我们认为,可扩展的合成计算机创建,结合大规模模拟,是长期生产力场景中代理自我改进和代理强化学习的基础性子结构,具有高度的前景。

英文摘要:

Realistic long-horizon productivity work is strongly conditioned on user-specific computer environments, where much of the work context is stored and organized through directory structures and content-rich artifacts. To scale synthetic data creation for such productivity scenarios, we introduce Synthetic Computers at Scale, a scalable methodology for creating such environments with realistic folder hierarchies and content-rich artifacts (e.g., documents, spreadsheets, and presentations). Conditioned on each synthetic computer, we run long-horizon simulations: one agent creates productivity objectives that are specific to the computer's user and require multiple professional deliverables and about a month of human work; another agent then acts as that user and keeps working across the computer -- for example, navigating the filesystem for grounding, coordinating with simulated collaborators, and producing professional artifacts -- until these objectives are completed. In preliminary experiments, we create 1,000 synthetic computers and run long-horizon simulations on them; each run requires over 8 hours of agent runtime and spans more than 2,000 turns on average. These simulations produce rich experiential learning signals, whose effectiveness is validated by significant improvements in agent performance on both in-domain and out-of-domain productivity evaluations. Given that personas are abundant at billion scale, this methodology can in principle scale to millions or even billions of synthetic user worlds with sufficient compute, enabling broader coverage of diverse professions, roles, contexts, environments, and productivity needs. We argue that scalable synthetic computer creation, together with at-scale simulations, is highly promising as a foundational substrate for agent self-improvement and agentic reinforcement learning in long-horizon productivity scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑