daVinci-Agency: 解锁长周期代理数据高效性
daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently
AI总结：
daVinci-Agency通过PR序列生成长周期代理数据，实现高效且高质量的监督学习，提升模型在复杂任务中的表现。
摘要：
尽管大语言模型（LLMs）在短周期任务上表现出色，但将其扩展到长周期代理工作流仍面临挑战。核心瓶颈在于训练数据的匮乏，这些数据能够捕捉到真实的长依赖结构和跨阶段的演化动态——现有的合成方法要么局限于受模型分布约束的单特征场景，要么导致高昂的人工标注成本，无法提供可扩展的高质量监督。我们通过重新概念化数据合成，从现实软件演化的角度出发。我们的关键发现：拉取请求（PR）序列自然地体现了长周期学习的监督信号。它们将复杂目标分解为可验证的提交单元，保持迭代过程中的功能一致性，并通过错误修复历史编码真实的细化模式。基于此，我们提出了daVinci-Agency，系统地从链式PR中挖掘结构化监督，通过三个相互关联的机制：（1）通过连续提交进行逐步任务分解；（2）通过统一的功能目标进行长期一致性强制；（3）从真实的错误修复轨迹中获得可验证的细化。与合成轨迹将每一步独立处理不同，daVinci-Agency的PR基础结构本质上保留了因果依赖性和迭代细化，这对于教授持续的目标导向行为至关重要，并能够自然地与项目级的完整周期任务建模对齐。所产生的轨迹规模庞大——平均达到85,000个标记和116次工具调用——但具有显著的数据效率：在239个daVinci-Agency样本上微调GLM-4.6在多个基准测试中均取得广泛改进，特别是在Toolathlon上实现了47%的相对提升。除了基准性能外，我们的分析证实...
英文摘要：
While Large Language Models (LLMs) excel at short-term tasks, scaling them to long-horizon agentic workflows remains challenging. The core bottleneck lies in the scarcity of training data that captures authentic long-dependency structures and cross-stage evolutionary dynamics--existing synthesis methods either confine to single-feature scenarios constrained by model distribution, or incur prohibitive human annotation costs, failing to provide scalable, high-quality supervision. We address this by reconceptualizing data synthesis through the lens of real-world software evolution. Our key insight: Pull Request (PR) sequences naturally embody the supervision signals for long-horizon learning. They decompose complex objectives into verifiable submission units, maintain functional coherence across iterations, and encode authentic refinement patterns through bug-fix histories. Building on this, we propose daVinci-Agency, which systematically mines structured supervision from chain-of-PRs through three interlocking mechanisms: (1) progressive task decomposition via continuous commits, (2) long-term consistency enforcement through unified functional objectives, and (3) verifiable refinement from authentic bug-fix trajectories. Unlike synthetic trajectories that treat each step independently, daVinci-Agency's PR-grounded structure inherently preserves the causal dependencies and iterative refinements essential for teaching persistent goal-directed behavior and enables natural alignment with project-level, full-cycle task modeling. The resulting trajectories are substantial--averaging 85k tokens and 116 tool calls--yet remarkably data-efficient: fine-tuning GLM-4.6 on 239 daVinci-Agency samples yields broad improvements across benchmarks, notably achieving a 47% relative gain on Toolathlon. Beyond benchmark performance, our analysis confirms...
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。
