Self-Evolving OpenClaw Workflow Playground and Benchmark Harness Model Card

这是可索引项目报告证据页：它保留 Self-Evolving OpenClaw Workflow Playground and Benchmark Harness Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。

Self-Evolving OpenClaw Workflow Playground and Benchmark Harness Model Card

1. Role in Self Evolve

longmans/self-evolve is a self-learning OpenClaw plugin that learns from feedback and turns runtime experience into reusable memory. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.

2. Working Principle

feedback detection -> reward scoring and learning gates -> Q-value updates plus episodic memory append -> local and remote retrieval on later turns

3. Evidence Path

web-observed GitHub page showed 96 stars, 5 forks, 27 commits, MIT license, OpenClaw plugin install flow, before_prompt_build and agent_end hooks, Q-value updates, episodic memories, and optional shared remote memory service. This iteration keeps freshness honest: the snapshot comes from the current public GitHub page, while shell GitHub API access remained blocked in this workspace.

4. Teaching Use

Use this card to explain Self-Evolving OpenClaw Workflow Playground and Benchmark Harness: it shows how harness/runtime/benchmark or memory/skill layers convert agent behavior into reproducible and auditable engineering workflows.

5. Limits

The repository was not cloned in this iteration; no benchmark run, plugin install, workflow execution, or agent loop experiment was executed. Counts and claims are visible public-page signals unless independently revalidated later.