Research map / Large language models / Agents, code and math
Prompt Optimization with Minimal Unlabeled Input via Meta-Reasoning
Yuran Sun, Chuan Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add abstract strategies (ablation) | MR.PEA · BBH sports_understanding | accuracy: 70.00 -> 85.60 | Improved |
| add abstract strategies (ablation) | MR.PEA · BBH temporal_sequences | accuracy: 81.60 -> 93.20 | Improved |
| add abstract strategies (ablation) | MR.PEA · BBH boolean_expressions | accuracy: 97.20 -> 98.80 | Improved |
| add evaluation criteria (ablation) | MR.PEA · BBH sports_understanding | accuracy: 78.40 -> 85.60 | Improved |
| add evaluation criteria (ablation) | MR.PEA · BBH boolean_expressions | accuracy: 98.00 -> 98.80 | Improved |
| add example generation (ablation) | MR.PEA · BBH sports_understanding | accuracy: 70.80 -> 85.60 | Improved |
| add example generation (ablation) | MR.PEA · BBH disambiguation_qa | accuracy: 59.60 -> 60.00 | Improved |
| add example generation (ablation) | MR.PEA · BBH temporal_sequences | accuracy: 92.00 -> 93.20 | Improved |
| add web search (ablation) | MR.PEA · BBH movie_recommendation | accuracy: 59.60 -> 64.40 | Improved |
| add web search (ablation) | MR.PEA · BBH ruin_names | accuracy: 69.20 -> 73.60 | Improved |
| add web search (ablation) | MR.PEA · BBH snarks | accuracy: 67.42 -> 74.16 | Improved |
| add web search (ablation) | MR.PEA · BBH Language | accuracy: 65.32 -> 67.55 | Improved |
Closest papers by meaning
- GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt Optimizers (ICLR 2025 · similarity 0.91)
- System Prompt Optimization with Meta-Learning (NeurIPS 2025 · similarity 0.91)
- Scaling Prompt Synthesis for Large Language Model Reasoning (ICML 2026 · similarity 0.90)
- How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation (NeurIPS 2025 · similarity 0.90)
- Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers (AAAI 2025 · similarity 0.90)
- PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization (ICLR 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
