菜单
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents - Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable...
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/hiyenwong/ai_collection --skill who-grades-the-grader-co-evolving-evaluation-metri命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Graph-native Python reimplementation of the Information Dynamics of Music (IDyOM) model that represents predictive memories as explicit graph objects for musical expectation modeling and network analysis.
Physics-aware end-to-end deep reinforcement learning methodology for quadcopter control with actuator dynamics modeling.
Reinforced Dreamer methodology for asymmetric reinforcement learning using latent guidance to improve world model representations and behaviors in model-based RL.
基于 SOC 职业分类
正在显示 SKILL.md
| name | who-grades-the-grader-co-evolving-evaluation-metri |
| description | Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents - Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable... |
| version | 1.0.0 |
| author | Xing Zhang, Guanghui Wang, Yanwei Cui et al. |
| arxiv_id | 2607.1279 |
| created | 2026-07-14T00:00:00.000Z |
| category | nlp-llm |
| tags | ["cs.AI","cs.CL","cs.MA"] |
| activation_keywords | ["grades","grader","evolving","evaluation","metrics","skills","self","improving","agents","agent"] |
Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable evaluation metric already exists. In many real applications it does not. We make three claims. First, metrics can be \emph{evolved}: our metric loop searches compositions of small drawback detectors under a full evolutionary lifecycle, trained to agree with a ten-item anchored reference set, regularized by consensus over unlabeled outputs, and audited against a held-out anchor it never reads, yielding a transparent, inspectable metric rather than an opaque judge. Second, since no metric exists to beat, the yardstick is recovering what an accurate metric would have enabled, and \emph{Double Ratchet}, our co-evolution of the metric with a lifecycle-managed skill loop, does so: across code generation (MBPP+), enterprise text-to-SQL (Spider~2.0-Snow), and reference-free report generation, it retains 88--110% of the held-out lift achieved by the same skill loop driven by ground truth or the best available rubric. Third, safety comes from anchor discipline plus outer audits: removing anchor guards collapses the metric into a vacuous detector while removing the lifecycle does not; and when evolved skills gamed the report rubric, an independent judge caught it, one detector repaired it, and a task-aware judge then preferred the evolved outputs over the pre-evolution baseline in 77% of decided pairs. We argue this failure-expecting architecture is the right default wherever no reliable automatic verifier exists.
grades, grader, evolving, evaluation, metrics, skills, self, improving, agents, agent
