Paper 2602.02619
daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently
- Published
- Feb 2026
- Research lab
- Independent
- Citations
- 3
- GitHub
- 38 stars
01 In brief
Summary
The paper introduces daVinci-Agency, a data synthesis paradigm for training LLM agents on long-horizon tasks.
It mines chains of semantically linked GitHub Pull Requests (PRs) to create training trajectories that capture task decomposition, long-term consistency, and iterative refinement.
The method constructs task chains from up to five PRs, yielding trajectories averaging 85k tokens and 116 tool calls.
Fine-tuning GLM-4.6 on only 239 such samples outperforms models trained on datasets up to 66k samples, achieving a 47% relative gain on Toolathlon and improvements on SWE-bench, DS-1000, and other benchmarks.
The approach also shows gains across Qwen3 models of various sizes.
Ablations confirm the importance of semantic PR chaining and rejection sampling.
The authors demonstrate that extending training trajectory length and inference-time tool call budgets further improves performance, establishing scaling laws for long-horizon agentic tasks.
The work positions daVinci-Agency as a scalable, data-efficient alternative to synthetic or manually annotated long-horizon training data.
02 From the paper
Abstract
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...