✨GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

📝 Summary:
GEPA is a prompt optimizer that uses natural language reflection to learn high-level rules from trial and error. It significantly outperforms RL methods like GRPO and MIPROv2, achieving better performance with up to 35x fewer rollouts.

🔹 Publication Date: Published on Jul 25, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2507.19457
• PDF: https://arxiv.org/pdf/2507.19457
• Project Page: https://gepa-ai.github.io/gepa/
• Github: https://github.com/gepa-ai/gepa

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#PromptEngineering #ReinforcementLearning #ArtificialIntelligence #MachineLearning #NLP

✨What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance

📝 Summary:
This study found that specific linguistic features in user queries correlate with LLM hallucination likelihood. Analyzing over 369000 queries, they identified a risk landscape where features like deep clause nesting increase risk, while clear intention decreases it. This paves the way for better ...

🔹 Publication Date: Published on Feb 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.20300
• PDF: https://arxiv.org/pdf/2602.20300
• Project Page: https://arxiv.org/abs/2602.20300

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLM #PromptEngineering #NLP #AIResearch #AIHallucination

✨Do What I Say: A Spoken Prompt Dataset for Instruction-Following

📝 Summary:
DoWhatISay is a new multilingual dataset of human-recorded spoken and written prompts for evaluating Speech Large Language Models. It reveals text prompts consistently outperform spoken prompts, except in speech-output tasks. This highlights the need for speech-based SLLM evaluation.

🔹 Publication Date: Published on Mar 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.09881
• PDF: https://arxiv.org/pdf/2603.09881
• Project Page: https://huggingface.co/collections/meetween/meetweens-research-papers
• Github: https://github.com/MaikeZuefle/DOWIS

✨ Datasets citing this paper:
• https://huggingface.co/datasets/maikezu/dowis

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#SLLM #SpeechAI #LLM #PromptEngineering #Dataset

✨Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral Specifications

📝 Summary:
TDAD is a methodology that compiles AI agent prompts from behavioral specifications using automated testing. This iterative process refines prompts to ensure measurable compliance, preventing regressions and policy violations for reliable production deployment.

🔹 Publication Date: Published on Mar 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.08806
• PDF: https://arxiv.org/pdf/2603.08806
• Project Page: https://www.alphaxiv.org/abs/2603.08806
• Github: https://github.com/f-labs-io/tdad-paper-code

✨ Datasets citing this paper:
• https://huggingface.co/datasets/f-labs-io/SpecSuite-Core

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AIAgents #PromptEngineering #TestDrivenDevelopment #AISafety #AIResearch

✨Tinted Frames: Question Framing Blinds Vision-Language Models

📝 Summary:
Vision-language models suffer selective blindness, where linguistic framing degrades visual attention and performance. Constrained framings reduce focus on relevant image regions. A new prompt-tuning method improves visual grounding and performance across different framings.

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19203
• PDF: https://arxiv.org/pdf/2603.19203
• Project Page: https://davidhalladay.github.io/tinted_frames_demo/
• Github: https://github.com/davidhalladay/Tinted-Frames

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VisionLanguageModels #PromptEngineering #AIAttention #DeepLearning #AIResearch

✨BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection

📝 Summary:
BEAVER is a training-free framework that improves long-context LLM inference using structure-aware hierarchical selection and dense tensor mapping. It maintains semantic integrity, achieves comparable performance to SOTA methods, and significantly reduces latency by 26.4x on large contexts.

🔹 Publication Date: Published on Mar 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19635
• PDF: https://arxiv.org/pdf/2603.19635
• Project Page: https://cslikai.cn/BEAVER/
• Github: https://github.com/JusperLee/BEAVER

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLM #AI #PromptEngineering #DeepLearning #ModelOptimization

✨REVERE: Reflective Evolving Research Engineer for Scientific Workflows

📝 Summary:
REVERE enhances research coding agent performance via reflective optimization and cumulative knowledge consolidation across multiple tasks. It overcomes prior prompt-optimization limits, achieving significant gains on research coding benchmarks and demonstrating agent evolution.

🔹 Publication Date: Published on Mar 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.20667
• PDF: https://arxiv.org/pdf/2603.20667

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AIAgents #ResearchAutomation #CodingAI #PromptEngineering #AgentEvolution

✨Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning

📝 Summary:
TRACE is a prompting method that enables MLLMs to perform 3D spatial reasoning by generating text-based representations of video environments. This improves spatial question answering and consistently outperforms prior strategies.

🔹 Publication Date: Published on Mar 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.23404
• PDF: https://arxiv.org/pdf/2603.23404

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#SpatialReasoning #MLLMs #AI #PromptEngineering #ComputerVision

✨Brevity Constraints Reverse Performance Hierarchies in Language Models

📝 Summary:
Large language models can underperform smaller ones due to verbose responses that introduce errors. Constraining output length reveals their superior latent capabilities, reversing performance hierarchies. This demands scale-aware prompt engineering for optimal performance.

🔹 Publication Date: Published on Mar 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.00025
• PDF: https://arxiv.org/pdf/2604.00025
• Github: https://github.com/logicsame/Brevity-Constraints-Reverse-Performance-Hierarchies-in-Language-Models

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLM #PromptEngineering #AI #MachineLearning #NLP

✨Adam's Law: Textual Frequency Law on Large Language Models

📝 Summary:
Adam's Law proposes a novel framework to improve LLM performance through textual frequency analysis. It introduces Textual Frequency Law for prompting/fine-tuning, Distillation for estimation, and Curriculum Training. Experiments demonstrate its effectiveness.

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02176
• PDF: https://arxiv.org/pdf/2604.02176
• Github: https://github.com/HongyuanLuke/frequencylaw

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLM #TextFrequency #PromptEngineering #NLP #DeepLearning