---
title: daVinci-Agency Paradigm
url: https://www.emergentmind.com/topics/davinci-agency-paradigm
type: topic
---

# daVinci-Agency Paradigm

The daVinci-Agency paradigm is a set of methodologies and frameworks for designing agentic artificial intelligence systems that excel in long-horizon, goal-directed workflows while rigorously preserving human agency and ensuring robust, modular decision-making. Originating in both surgical human–AI teaming and software development, daVinci-Agency reframes agent coordination, supervision signal extraction, and safety guarantees to address complex, multi-stage environments. The paradigm tightly integrates hierarchical multi-agent orchestration, agency-preserving objectives, long-term consistency constraints, and authentic supervisory data derived from real-world project evolution [2511.07392, 2305.19223, 2602.02619].

## 1. Foundational Principles and Formal Definitions

At the core of daVinci-Agency is an explicit commitment to agency preservation in AI–human interaction. Agency is mathematically defined as $agency(s) = \lvert A(s) \rvert$, where $A(s)$ is the set of actions available to the human at state $s$. The forward-looking agency metric evaluates accumulated future option breadth:

$$
E^{\pi}(s) = \mathbb{E}\left[\sum_{t=0}^\infty \gamma^t\,agency(s_t)\right], \quad 0 \leq \gamma < 1
$$

For joint human–AI policies $\pi_\text{sys}$ and a human-alone baseline $\pi_H$, interactions are *agency-preserving* if, for all reachable states $s$,

$$
E^{\pi_\text{sys}}(s) \geq E^{\pi_H}(s)
$$

This formalism underpins decision-making rules for both software agents and safety-critical systems, ensuring that the cumulative capacity for user-directed choice is never diminished by AI intervention [2305.19223]. Deviations at each timestep are measured via the “agency-error” $\delta_t^A$, analogous to TD error in reinforcement learning.

## 2. Hierarchical Multi-Agent Architectures

The paradigm operationalizes agent orchestration through a layered architecture, exemplified by the Surgical Agent Orchestration Platform (SAOP):

- **Orchestration Agent:** Implements high-level workflow functions with modular subcomponents:
  - **Profile Module:** Encodes top-level objectives (e.g., valid wake-word detection, workflow boundaries, agent plug-and-play).
  - **Memory Module:** Tracks command history and current state, spanning global (across video clips) and local (within a clip) memory.
  - **Decision Module:** Leverages LLMs (e.g., Gemma3 with chain-of-thought prompting) to select workflow actions via a probabilistic JSON API, applying argmax over per-function probabilities.
  - **Feedback Module:** Monitors invalid cycles, restricts re-entries to a strict upper bound (≤3), and enforces clarity in speech-command dialogue.

- **Task-Specific Agents:**
  - **Information Retrieval (IR):** Extracts patient clinical data for overlay, making field selection decisions via LLM-inferred distributions $\pi_\theta(a|x,i)$ and $\varphi_\theta(j|x,i,a)$.
  - **Image Viewer (IV):** Navigates and zooms through CT scan volumes; state transitions are governed by policy factorization and deterministic action–parameter selection.
  - **Anatomy Rendering (AR):** Manipulates 3D anatomical reconstructions with continuous state parameters for zoom, rotation, and structure visibility, ensuring temporally coherent action via smooth interpolation.

*This architectural decoupling ensures both robustness and extensibility, supporting new data modalities and workflow configurations without cross-component re-engineering* [2511.07392].

## 3. Long-Horizon Agentic Supervision via Real-World Software Evolution

daVinci-Agency reconceptualizes agentic output supervision by mining *Pull Request* (PR) chains from mature software repositories. Each PR chain, $S = (P_1, P_2, \dots, P_n)$ with $P_i = (C_i, D_i)$, encodes:

- **Progressive Task Decomposition:** Serial commits naturally decompose project-scale objectives into granular, verifiable actions.
- **Long-Term Consistency Enforcement:** Cross-PR consistency with the global project goal $G$ is enforced through embedding-based similarity constraints and temporal drift regularization.
- **Verifiable Refinement:** Authentic bug-fix pairs $(P_j, P_{j+1})$ allow targeted supervision on the refinement and debugging subskills via performance delta metrics $\Delta_\text{perf}$.

Agentic policies $\pi_\theta$ are trained to jointly minimize three losses—$\mathcal{L}_{\mathrm{decomp}}(\theta)$ for decomposition, $\mathcal{L}_{\mathrm{consist}}(\theta)$ for consistency, and $\mathcal{L}_{\mathrm{refine}}(\theta)$ for refinement—weighted to promote robust long-horizon task execution [2602.02619].

## 4. Evaluation and Quantitative Performance

### Multi-Level Orchestration Evaluation Metric (MOEM)

The MOEM framework provides rigorous assessment of the orchestration pipeline:

- **Stage-Level Accuracy**: For each stage $s$, $Accuracy_s = (1/N) \sum_{i=1}^N o_{i,s}$
- **Workflow-Level Success**: Strict, single-pass, and multi-pass rates ($SR_\text{strict}$, etc.) evaluated over complete end-to-end flows
- **Category-Level Success**: $\mathrm{SR}_{\text{multi}}(c)$ computed for command structural, type, and expression categories

Representative results in a voice-controlled surgical environment:

| Stage                    | Accuracy or Success Rate |
|--------------------------|:-----------------------:|
| Real-Time Audio (wake)   | 88.6%                   |
| STT transcription        | ~81% (raw), CC ≈97%     |
| Command Reasoning        | ≈98%                    |
| Action Determination     | ≈95%                    |
| Orchestration Flow       | 100%                    |
| SR_multi-pass            | 95.8%                   |

*Category-level robustness metrics confirm high performance even under paraphrased and composite command input, with failure cases concentrated in composite+paraphrase intersections* [2511.07392].

### Software Agentic Workflows

With only 239 curated PR chains (average 85,000 tokens, 116 tool calls), models trained under the daVinci-Agency paradigm achieve a 47% relative gain on the Toolathlon benchmark and robust improvements across SWE-bench, DS-1000, $\tau^2$-Bench, and SciCode-MP. Token and tool call efficiency scales favorably relative to synthetic or flat-trajectory baselines [2602.02619].

## 5. Agency-Safe AI Design Principles

To guarantee agency preservation and robust performance, four design pillars are articulated [2305.19223]:

1. **Explicit Agency-Augmented Objective:** Reward functions include an explicit forward-looking agency term; $R_{AI}(s,a) = R_{task}(s,a) + \lambda[E^{\pi_{sys}}(s) - E^{\pi_H}(s)]$.
2. **Baseline Agency Tracking & Auditing:** Continuous logging and comparison of $E^{\pi_{sys}}$ vs. $E^{\pi_H}$, enabling post-hoc verification and regulatory compliance.
3. **Transparent, Choice-Preserving Interfaces:** UI presents alternative actions and explicit “agency scores” for each trajectory.
4. **Conservative Agency Policy Under Uncertainty:** Under model uncertainty, the agent defaults to policies that preserve maximal worst-case agency, solving a robust MDP for conservative deployment.

## 6. Data Mining and Practical Implementation Pipeline

The structured collection of long-horizon supervision proceeds via:

- **Repo Selection:** ~61,800 PRs mined from repositories such as numpy, apache/pulsar, scipy.
- **Dependency-Aware PR-Chain Construction:** Construction of directed acyclic PR dependency graphs to extract multi-PR chains.
- **Query Synthesis:** Sub-queries for each PR, omitting implementation but conveying change intent for semantic alignment.
- **Rollout and Rejection Sampling:** GLM-4.6-based rollouts, state carryover, and strict acceptance thresholds ($s\ge 0.8$) for dataset quality.

*This pipeline underpins the efficient acquisition of authentic, causally-structured agentic trajectories for LLM fine-tuning* [2602.02619].

## 7. Broader Implications and Future Directions

The daVinci-Agency paradigm supports multi-domain generalization. In surgery, modular orchestration yields robustness to diverse command expressions and plug-and-play modality extension (e.g., intraoperative ultrasound), while data-efficient long-horizon learning in software unlocks persistent, project-scale goal pursuit.

Outlined future directions include:

- Integration of agency-preserving frameworks into RL from internal states, tracking variables such as user confidence and cognitive load.
- Formalization of algorithmic human rights within AI policy spaces.
- Mechanistic interpretability of agency within neural architectures, enabling third-party auditing.
- Extension to multilingual and mixed-modality command environments, necessitating advances in STT adaptation and transliteration.

A plausible implication is that wide adoption of daVinci-Agency’s principles can mitigate agency erosion in both supervised and reinforcement learning contexts, promoting human–AI collaboration where user autonomy and long-term options are preserved or enhanced.

Source: https://www.emergentmind.com/topics/davinci-agency-paradigm