# daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently

arXiv: https://arxiv.org/abs/2602.02619 · HTML: https://mlsanity.com/paper/2602.02619/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 22 of 22)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [MimicPlay: Long-Horizon Imitation Learning by Watching Human Play](https://mlsanity.com/paper/2302.12422/) (2023)
- [SciCode: A Research Coding Benchmark Curated by Scientists](https://mlsanity.com/paper/2407.13168/) (2024)
- [SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents](https://mlsanity.com/paper/2505.20411/) (2025)
- [Question Decomposition Improves the Faithfulness of Model-Generated Reasoning](https://mlsanity.com/paper/2307.11768/) (2023)
- [The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution](https://mlsanity.com/paper/2510.25726/) (2025)
- [Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL](https://mlsanity.com/paper/2508.13167/) (2025)
- [AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts](https://mlsanity.com/paper/2601.11044/) (2026)
- [UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios](https://mlsanity.com/paper/2509.21766/) (2025)
- [Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills](https://mlsanity.com/paper/2512.16301/) (2025)
- [InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research](https://mlsanity.com/paper/2510.27598/) (2025)
- [daVinci-Dev: Agent-native Mid-training for Software Engineering](https://mlsanity.com/paper/2601.18418/) (2026)
- [LIMI: Less is More for Agency](https://mlsanity.com/paper/2509.17567/) (2025)
- [A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning](https://mlsanity.com/paper/2510.01132/) (2025)
- [Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction](https://mlsanity.com/paper/2512.04987/) (2025)
- [Can Students Beyond The Teacher? Distilling Knowledge from Teacher's Bias](https://mlsanity.com/paper/2412.09874/) (2024)

## Built on by (most cited first, 3 of 3)

- [daVinci-Env: Open SWE Environment Synthesis at Scale](https://mlsanity.com/paper/2603.13023/) (2026)
- [The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards](https://mlsanity.com/paper/2607.24063/) (2026)
- [LU-500: A Logo Benchmark for Concept Unlearning](https://mlsanity.com/paper/2607.24101/) (2026)

## Abstract (arXiv)

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...