# AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows

arXiv: https://arxiv.org/abs/2607.16345 · HTML: https://mlsanity.com/paper/2607.16345/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Placed in

- LLM agents and tool use / [Agent skill learning and evolution](https://mlsanity.com/agents/agent-skill-learning-and-evolution/)

## Builds on (most cited first, 11 of 11)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [Prediction-Powered Inference](https://mlsanity.com/paper/2301.09633/) (2023)
- [Self-Evaluation Improves Selective Generation in Large Language Models](https://mlsanity.com/paper/2312.09300/) (2023)

## Built on by (most cited first, 2 of 2)

- [Evaluating Skills, Not Just Agents: Agentic Continuous Evaluation of Skills](https://mlsanity.com/paper/2608.20614/) (2026)
- [A Contract-Centered Architecture for Scalable and Manageable Agentic Runtimes](https://mlsanity.com/paper/2608.27086/) (2026)

## Abstract (arXiv)

Modern agentic systems increasingly rely on skills: installable packages of natural language and code that teach an LLM agent to perform a domain task. As skill repositories grow, developers need automated quality signals on every change, yet evaluation today is largely anecdotal: a developer asks an agent to "try the skill," watches a demo, and forms a subjective impression. This yields neither reproducibility across runs nor comparability across versions, and scales poorly to marketplaces where one regression can silently break dozens of downstream workflows. We present AEVAL (Agentic Evaluation), a CI-integrated framework that replaces this practice with a deterministic, reproducible test pipeline for agentic skills. Every skill change triggers a test event: the skill runs against a developer declared evaluation contract inside an automated executor, emitting a structured, evidence grounded quality signal that downstream CI can route on. A key ingredient is a structural separation between executor and grader, preventing a subtle but pervasive failure mode: an agent that silently self-corrects during execution and then grades its own patched outputs as passing. Our contributions are: (i) a deterministic, change-triggered evaluation protocol with per-skill contracts and per-run artifact schemas; (ii) a formalization of self correction bias as a distinct failure mode of naive agentic evaluators; (iii) an executor/grader separation with a first-attempt grading rule and explicit self-correction tracking; and (iv) a tiered, grounded evidence fix suggestion scheme (LV1 causal, LV2 quality) posted as inline merge-request comments. Validated on real skills in a production agentic stack across multiple agent SDKs, AEVAL converts spurious 100% pass rates into reproducible first-attempt fail signals with an auditable record of every executor fix.