Scientific Agents: Evaluating Profession-Specific System Prompts on Scientific Tasks
中文摘要
研究评估了503个专业代理配置文件,发现详细的系统提示词增加了Token消耗和成本,但并未带来一致的准确率提升。
English Summary
Researchers evaluated 503 profession-specific agent profiles, finding that detailed system prompts increase token costs without consistently improving accuracy compared to simpler prompts.
arXiv:2610.00084v1 Announce Type: new Abstract: 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 agent harness. We compare matched profiles with four controls: a minimal baseline ("You are a helpful assistant"), the profile's opening role sentence, a generic scientific rigor guide, and a profile from an unrelated domain. Across nine text-based science benchmarks (4,531 sampled questions, 100 matched profiles), 4,488 items completed all five conditions after API-error retries, scored with automated, rule-based grading. The average profile-baseline accuracy difference is -0.6 percentage points (95% bootstrap interval [-1.5, +0.2] across fixed tasks), and no benchmark shows a statistically clear improvement. Matched profiles produced 1.5-2.3 times as many output tokens and cost 2.2-4.5 times more per successful call. On 60 tool-using BioMysteryBench bioinformatics problems (three runs each for baseline and profile), mean solve rates were 46.7% with the profile an…