Stateful Continual-Learning Benchmark for LLM Agents Model Card

这是可索引项目报告证据页：它保留 Stateful Continual-Learning Benchmark for LLM Agents 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。

Stateful Continual-Learning Benchmark for LLM Agents Model Card

1. Role in Self Evolve

Arc-Computer/CL-Bench is a benchmark framework for evaluating LLM agent continual learning in stateful environments with CRM-style workflows. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.

2. Working Principle

place agents inside stateful multi-turn workflows -> mutate persistent entities under production-style constraints -> evaluate adaptation and reliability under cross-turn dependencies -> use continual-learning pressure instead of one-shot benchmark snapshots

3. Evidence Path

web-observed GitHub page showed 19 stars, 3 forks, 50 commits, Apache-2.0 license, CRM-style continual-learning workflows, 1,200+ conversations, and explicit evaluation harness support. 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 Stateful Continual-Learning Benchmark for LLM Agents: 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.