The paper proposes a multi-agent loop (instructor, follower, feedback) to auto-generate human-readable system prompts, claiming good benchmark performance and readability, but the supporting experiments are not reproducible from the text.
Avail- able: https://portkey.ai/blog/the-complete-guide-to-prompt-engineering
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models
The paper proposes a multi-agent loop (instructor, follower, feedback) to auto-generate human-readable system prompts, claiming good benchmark performance and readability, but the supporting experiments are not reproducible from the text.