AEC Bench Model Card
这是可索引项目报告证据页：它保留 AEC Bench 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。
AEC Bench Model Card
| Field | Value |
|---|---|
| Repository | nomic-ai/aec-bench |
| Category | Agentic Context Engineering Benchmark Suite |
| Stars / forks snapshot | 54 / 3 |
| Language | Python |
| License | Apache-2.0 |
| Raw capture | raw-github/nomic-ai_aec-bench.md |
| Updated by | hourly public metadata update, 2026-05-30 13:16 +0800 |
1. Role in Self Evolve
aec-bench is an agentic context engineering benchmark suite for measuring long-context agent behavior and retrieval-aware execution quality. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.
2. Working Principle
construct realistic context-heavy agent tasks -> compare retrieval, memory, and orchestration strategies -> benchmark long-context reasoning under controlled settings -> convert benchmark outcomes into actionable harness/memory optimizations
3. Evidence Path
web-observed GitHub page showed 54 stars, 3 forks, 15 commits, Apache-2.0 license, and README framing around benchmark-heavy agent context evaluation. Shell GitHub API access remained blocked by DNS and local gh auth was invalid, so this card treats the snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Agentic Context Engineering Benchmark Suite: it shows how harness/runtime/benchmark 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/search signals unless independently revalidated later.