SkillOpt – Executive Strategy for Self-Evolving Agent Skills

SkillOpt | Executive Strategy for Self-Evolving Agent Skills

Text-space optimization for frozen agents SkillOpt

Executive Strategy for Self-Evolving Agent Skills. SkillOpt treats a compact natural-language skill document as the trainable state of a frozen language agent, then learns that document through rollouts, reflection, bounded edits, and held-out validation gates.

Core Idea Method View Results

Code Repo

Paper

Video

Related project SkillLens studies model-generated agent skills. A companion project page from Microsoft Research.

Main result

52 /52

Best or tied-best in every model x benchmark and harness x benchmark setting.

Target models

Benchmarks

Harnesses Codex + Claude Code

Project Video

SkillOpt in motion.

A short visual overview of how SkillOpt treats natural-language skills as trainable artifacts: roll out, reflect, edit, validate, and export.

Promotional video for the SkillOpt project page. The static paper teaser is shown below for high-resolution inspection.

Paper Teaser

The core loop at a glance.

The teaser summarizes the SkillOpt training loop: rollout evidence, optimizer-side reflection, bounded skill edits, validation gating, and the exported reusable skill.

Figure from the SkillOpt paper. On small screens, the figure area scrolls horizontally to preserve the original details.

01 / Core Idea

Train the procedure, not the weights.

SkillOpt makes the skill document itself the optimization target. The target model, backend, and harness stay fixed; the procedure that guides evidence gathering, tool use, verification, and output formatting evolves.

A skill is external state for an agent.

Instead of fine-tuning a model or hand-maintaining prompts, SkillOpt runs the frozen agent on scored batches, asks a separate optimizer model to propose structured edits, and accepts a candidate only when validation performance improves.

Frozen target model Optimizer model Add / delete / replace edits Held-out gate

Rollout The target model executes tasks with the current skill and records scored trajectories.

Reflect The optimizer analyzes success and failure minibatches to find reusable procedures.

Edit Candidate add, delete, and replace operations are merged and ranked under a budget.

Gate The candidate skill is kept only if it improves held-out selection performance.

02 / Method

A training loop for natural-language skills.

The loop deliberately mirrors a learning algorithm: rollout evidence acts like a forward pass, reflection acts like a language-level backward pass, and the textual learning rate bounds how far the skill can move.

Evidence

Rollout batches capture messages, tool calls, verifier feedback, task metadata, and final scores.

Minibatches

Failures and successes are reflected separately so edits correct recurring errors while preserving working behavior.

Bounded Edits

An edit budget functions as a textual learning rate, preventing useful rules from being overwritten by broad rewrites.

Memory

Rejected edits, slow update, and optimizer-side meta skill provide longer-horizon feedback without bloating deployment.

SkillOpt pipeline from the paper. The frozen target model executes with the current skill; the optimizer model proposes bounded edits; held-out validation decides whether the candidate becomes the new current skill.

03 / Main Results

SkillOpt improves GPT and Qwen target models.

The table reports main-result gains across target models and execution harnesses, comparing no-skill execution with the final SkillOpt skill on held-out test splits.

Target model Harness SearchQA Sheet Office DocVQA LiveMath ALFWorld Avg gain

GPT-5.5 Direct chat +9.6 +38.9 +39.0 +12.4 +29.3 +11.9 +23.5

GPT-5.4 Direct chat +6.2 +21.1 +12.8 +13.6 +7.2 +15.6 +12.8

GPT-5.4-mini Direct chat +4.3 +11.4 +26.7 +16.5 +4.8 +12.7 +12.7

GPT-5.4-nano Direct chat +19.0 +8.2 +33.7 +49.4 +4.0 +35.1 +24.9

GPT-5.2 Direct chat +11.2 +18.9 +21.5 +16.5 +15.2 +16.4 +16.6

Qwen3.5-4B Direct chat +3.1 +14.6 +15.2 +2.1 +29.6 +50.7 +19.2

Qwen3.6-35B-A3B Direct chat +7.6 +9.3 +1.2 +3.8 +10.4 +22.4 +9.1

GPT-5.5 Codex +5.5 +57.5 +12.8 +5.0 +28.0 N/A +21.8

GPT-5.5 Claude Code +4.0 +58.3 +13.9 +3.5 +13.3 N/A +18.6

Method comparison SkillOpt clears the strongest baseline on every benchmark.

04 / Ablations

The controls are doing real work.

The paper isolates the optimizer components that keep skill learning stable: enough evidence, bounded textual updates, rejected-edit feedback, slow update, and optimizer-side memory.

Component Setting SearchQA Spreadsheet LiveMath

Learning rate lr=4 default 87.1 77.5 61.3

Learning rate without lr 84.6 75.7 57.3

Rejected buffer with buffer 87.1 77.5 61.3

Rejected buffer without buffer 85.5 72.9 58.9

Update memory meta skill + slow update 87.1 77.5 61.3

Update memory without both 86.3 55.0 59.7

What the ablations say

Bounded Textual learning rates prevent destructive rewrites while keeping enough plasticity to learn new...

SkillOpt – Executive Strategy for Self-Evolving Agent Skills

Related Articles

Amazon, Facebook, FBI have access to a private intelligence-sharing network

SpaceX not the behemoth everyone thought

The Mirror Is Part of the Machine

Elevated error rates on requests to multiple models

Donald Trump and sons to be 'forever' exempt from tax audits