NexForge：通过需求优先合成扩展可执行智能体任务
NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs
浏览论文内容
中文总结 AI 辅助
研究针对可执行智能体训练数据扩展瓶颈，提出需求优先框架NexForge，通过需求发现、任务编译等步骤生成训练数据，提升了模型在多个基准测试中的性能，助力Nex-N2模型达到开源先进水平。
中文摘要 AI 辅助
扩展可执行智能体训练数据受限于基于底层的方法，这些方法将任务生成与预定义工具、存储库或技能图绑定。我们引入了NexForge，这是一个需求优先的框架，可将自由形式的能力需求编译为可执行智能体训练数据。NexForge首先进行基于研究的需求发现，然后应用分布感知任务编译，自动检索或构建实现每个任务所需的文件等，接着进行教师展开收集和轨迹蒸馏。相同的管道在无特定领域基础设施的情况下，生成了大量任务，提升了模型在不同基准测试中的性能，还助力了Nex-N2系列模型的训练，达到了开源性能的先进水平。
英文摘要
Scaling executable agent training data for LLM post-training is bottlenecked by substrate-bound methods that tie task generation to predefined tools, repositories, or skill graphs: expanding coverage requires manual substrate engineering, each new domain demands a bespoke pipeline, and the resulting task distributions often reflect substrate biases rather than real-world demand. We introduce NexForge, a requirement-driven framework that takes high-level capability requirements as input and synthesizes diverse, executable agent tasks and expert trajectories for SFT. NexForge first investigates real-world demand to construct scenarios and task profiles, then performs distribution-aware compilation to generate task directives. For each directive, NexForge automatically retrieves or constructs the required files, dependencies, and runtime configurations, and finally collects expert rollouts to produce training trajectories. Without domain-specific infrastructure, NexForge produces 3.6K terminal and 2K office tasks, improving Qwen3.5-35B-A3B Base from 22.5\% to 52.0\% on Terminal-Bench 2.0 and from 813 to 1338 Elo on GDPval; scaling further to 43.2K terminal tasks yields 58.4\%, on par with Claude Opus 4.6 equipped with Claude Code. Scaled further, NexForge-synthesized data contributes to the training of Nex-N2, a family of publicly available agent models that lift Qwen3.5-397B-A17B to 75.3\% on Terminal-Bench 2.1 and to 1585 Elo on GDPval---achieving state-of-the-art open-source performance and surpassing several frontier proprietary systems. Nex-N2 models are available at https://nex.sii.edu.cn/.
发表机构
- East China Normal University（华东师范大学）
- Fudan University（复旦大学）
- Shanghai Qiji Zhifeng Co., Ltd（上海齐迹智峰有限公司）
机构由 AI 辅助整理，请以论文原文为准。
