# SkillOpt: Executive Strategy for Self-Evolving Agent Skills

> SkillOpt introduces the first systematic text-space optimizer for agent skills, achieving state-of-the-art performance across benchmarks by treating the skill document as a trainable external state for a frozen agent.

- **Source:** [arXiv](https://arxiv.org/abs/2605.23904)
- **Published:** 2026-05-26
- **Permalink:** https://picx.dev/p/pUAERe
- **Whiteboard:** https://picx.dev/p/pUAERe/image

## Summary

# SkillOpt: Executive Strategy for Self-Evolving Agent Skills - Summary

## Summary (Overview)
*   **Core Innovation**: SkillOpt is the first systematic, controllable text-space optimizer for agent skills, treating the skill document as an external, trainable state for a frozen agent, analogous to weight-space optimization in deep learning.
*   **Key Mechanism**: A separate optimizer model converts scored execution rollouts into bounded add/delete/replace edits on a skill document. Edits are accepted only if they strictly improve a held-out validation score, ensuring stable, controlled optimization.
*   **Empirical Dominance**: Evaluated across 6 benchmarks, 7 target models, and 3 execution harnesses, SkillOpt is the best or tied-best method on all 52 evaluated (model, benchmark, harness) cells, significantly outperforming all baselines.
*   **Strong Performance Gains**: On GPT-5.5, it lifts the average no-skill accuracy by +23.5 points in direct chat, +24.8 points inside the Codex agentic loop, and +19.1 points inside Claude Code.
*   **Transferable Artifacts**: Optimized skills retain value when transferred across model scales, between different execution environments (Codex/Claude Code), and to nearby math benchmarks without further optimization.

## Introduction and Theoretical Foundation
Agent skills are natural-language artifacts that package procedures, domain heuristics, and tool policies, allowing a frozen agent to adapt through external text. Current methods for skill creation—hand-crafting, one-shot generation, or loosely controlled self-revision—lack the discipline and reliability of a deep-learning optimizer.

The paper argues that skills should be **trained as the external state of a frozen agent**, applying optimization principles (batches, learning rates, validation) to the text space. The core analogy is operational:
*   **Skill document** ↔ Model parameters
*   **Trajectory-derived edit direction** ↔ Gradient
*   **Edit budget** ↔ Learning rate
*   **Held-out selection gate** ↔ Validation check

**SkillOpt** formalizes this by introducing a harness-agnostic optimizer with rollout batches, reflection minibatches, structured edits, textual learning rates, validation gating, rejected-edit buffers, and epoch-wise slow/meta updates. The output is a compact, reusable `best_skill.md` file that adds zero inference-time cost.

## Methodology
The problem is defined with a frozen target model $M$, a harness $h$, a task $x$, and a skill $s$. Execution produces a trajectory $\tau$ and a scalar score $r$:
$$(\tau(s), r(s)) = h(M, x, s), \quad r(s) \in [0, 1]$$
Given splits $D_{tr}, D_{sel}, D_{test}$, the goal is to find the best skill $s^\star_{sel}$ on the selection split and report final performance on the test split:
$$s^\star_{sel} = \arg \max_{s \in \mathcal{C}(D_{tr})} \frac{1}{|D_{sel}|} \sum_{x \in D_{sel}} r(s)$$
$$\text{Test}(s^\star_{sel}) = \frac{1}{|D_{test}|} \sum_{x \in D_{test}} r(s^\star_{sel})$$

The SkillOpt pipeline consists of several key components:
1.  **Forward Pass (Rollout Evidence)**: The target model executes a rollout batch from $D_{tr}$ with the current skill, generating trajectories.
2.  **Backward Pass (Minibatch Reflection)**: The optimizer model analyzes successes and failures in minibatches, proposing structured `add/delete/replace` edits.
3.  **Bounded Text Updates**: An edit budget $L_t$ (the textual learning rate) limits the number of edits applied per step. Edits are ranked and clipped.
4.  **Validation Gate & Rejected-Edit Buffer**: Every candidate skill is evaluated on $D_{sel}$. It is accepted only if it improves the selection score. Rejected edits become negative feedback for future updates.
5.  **Epoch-Wise Slow/Meta Update**: At epoch boundaries, the optimizer compares performance across epochs and writes longitudinal guidance into a protected section of the skill, capturing durable lessons.

The method is harness-agnostic through a lightweight adapter interface.

## Empirical Validation / Results
The evaluation answers four questions across six benchmarks (SearchQA, SpreadsheetBench, OfficeQA, DocVQA, LiveMathematicianBench, ALFWorld), seven target models (GPT-5.5, 5.4, 5.4-mini, 5.4-nano, 5.2, Qwen3.5-4B, Qwen3.6-35B-A3B), and three execution modes (direct chat, Codex harness, Claude Code harness).

### Main Results
**Table 1** presents the comprehensive results. Key findings:
*   SkillOpt is **best or tied-best on all 52 evaluated cells**.
*   On GPT-5.5 direct chat, it achieves an average gain of **+23.5 points** over no skill, lifting scores from 58.8 to 82.3.
*   It outperforms an oracle that picks the best per-cell baseline (human, LLM, Trace2Skill, TextGrad, GEPA, EvoSkill) by **+5.4 points on average**.
*   Gains are substantial across model scales, with smaller models (e.g., GPT-5.4-nano) showing the largest relative improvements (e.g., ALFWorld 34.3 → 69.4).
*   The method is equally effective inside tool-backed execution loops (Codex, Claude Code).

### Ablations and Analysis
**Table 2 & 3** and **Figure 3** analyze design choices:
*   Gains are relatively insensitive to exact batch sizes but require sufficient evidence.
*   **Bounded textual learning rates** are crucial. The "without lr" ablation performs worse.
*   The **validation gate, rejected-edit buffer, and epoch-wise slow/meta update** are critical stabilizers. Removing slow/meta update dropped SpreadsheetBench performance by -22.5 points.
*   Performance evolves stably across epochs, with validation selection aligning with test generalization.

### Transfer Experiments
**Table 4** demonstrates the portability of optimized skill artifacts:
*   **Cross-Model Transfer**: Skills trained on a source model (e.g., GPT-5.4) provide positive gains when deployed on smaller target models (e.g., GPT-5.4-mini, nano).
*   **Cross-Harness Transfer**: A SpreadsheetBench skill trained in Codex transfers to Claude Code with a **+59.7 point gain**.
*   **Cross-Benchmark Transfer**: A skill trained on OlympiadBench provides positive gains on the related Omni-MATH benchmark.

### Optimizer Strength and Skill Characteristics
**Table 5** shows that a stronger frontier optimizer (GPT-5.5) yields larger gains, but a target-matched optimizer still recovers 56–74% of the gain, confirming the loop's intrinsic value.

**Table 6** and **Figure 4** characterize the learned artifacts:
*   **Compact**: Final skills range from **379 to 1,995 tokens**.
*   **Edit-Economical**: Gains come from only **1–4 accepted edits** per benchmark.
*   **Procedural & Inspectable**: Learned rules encode generalizable procedures (e.g., "Inspect workbook structure and formulas, then write evaluated static values...").

## Theoretical and Practical Implications
*   **Skill as a Trainable State**: The paper establishes a new paradigm where the skill document itself is the primary object of optimization, enabling controlled, reproducible adaptation for frozen agents.
*   **Harness-Agnostic Optimization**: By separating the optimizer from the execution harness, SkillOpt provides a general-purpose adaptation layer applicable across diverse agent environments.
*   **Cost-Effective Deployment**: The one-time training cost produces a compact, static artifact (`best_skill.md`) that adds zero overhead at deployment and can be audited, edited, and reused.
*   **Empirical Superiority**: The comprehensive results demonstrate that systematic, validation-gated text-space optimization outperforms existing methods for skill/prompt improvement, especially on procedural tasks.

## Conclusion
SkillOpt introduces a controlled text-space optimization loop for agent skills, applying deep-learning-style discipline (batches, learning rates, validation) to a natural-language artifact. It delivers state-of-the-art performance across a broad range of models, benchmarks, and execution environments. The resulting skills are compact, interpretable, and transferable, positioning them as a practical, weight-free domain adaptation layer for frontier agents.

**Future directions** include extending to skill libraries, preference-driven gates for open-ended tasks, and self-distillation of skills back into model weights.

---

_Markdown view of https://picx.dev/p/pUAERe, served by PicX — AI-generated visual whiteboard summaries of research papers._