# Scientific Agents: Evaluating Profession-Specific System Prompts on Scientific Tasks

> 全文为英语

**Published:** 2026年10月2日
**Author:** Timothy Kassis
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/scientific-agents-evaluating-profession-specific-system-prompts-on-scien

Detailed profession-specific system prompts raise token use and estimated cost per response without a consistent accuracy gain. We evaluate Scientific Agents, an open-source corpus of 503 profession-specific AGENTS.md profiles, with Gemini 3.8 Flash via OpenRouter in the Pi…

> 内容来自原始来源： **arXiv — cs.AI**
> [在 arXiv — cs.AI 阅读全文](https://arxiv.org/abs/2610.00084)

**标签：** #Google DeepMind #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*