InternAgent-1.5 Model Card
这是可索引项目报告证据页：它保留 InternAgent-1.5 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。
InternAgent-1.5 Model Card
| Field | Value |
|---|---|
| Repository | InternScience/InternAgent |
| Category | Autonomous Scientific Discovery Agent Framework |
| Stars / forks snapshot | 1300 / 116 |
| Language | Python |
| License | Apache-2.0 |
| Raw capture | raw-github/internscience_internagent.md |
| Updated by | hourly public metadata update, 2026-05-27 09:59 +0800 |
1. Role in Self Evolve
InternAgent-1.5 is a unified multi-agent framework for long-horizon autonomous scientific discovery, spanning discovery runs, QA deep research, and reproducible task execution. It matters because self-evolving agents need repeatable harness control, measurable feedback loops, and reusable skill procedures before claiming stable improvement.
2. Working Principle
idea generation -> method construction -> experiment planning and execution -> benchmark evaluation -> memory-informed next iteration
3. Evidence Path
web-observed GitHub page (redirect from Alpha-Innovator/InternAgent to InternScience/InternAgent) showed 1.3k stars, 116 forks, 45 commits, Apache-2.0 license, and README news covering open-sourced 1.5 features plus deep-research/benchmark positioning. 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 Autonomous Scientific Discovery Agent Framework: 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.