{"slug": "tapr-enhancing-llm-performance-with-a-task-aware-prompt-rewriter", "title": "TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter", "summary": "Researchers introduced Task-Aware Prompt Rewriter (TAPR), a model that reformulates user prompts into task-optimized prompts to improve downstream LLM performance, trained via reinforcement learning with Group Relative Policy Optimization (GRPO) and rewards from LLM-as-judge evaluations. Fine-tuning Phi-4-mini-instruct as the base model produced clearer prompts, yielding higher accuracy on benchmarks such as Natural Questions and GSM8K. The code is available on GitHub.", "body_md": "arXiv:2607.28657v1 Announce Type: new\nAbstract: Large Language Models (LLMs) often require carefully crafted prompts to unlock their full potential, which can be a barrier for non-expert users. This work addresses the challenge by introducing a Task-Aware Prompt Rewriter (TAPR), a model that reformulates user prompts into task-optimized prompts with the explicit goal of improving downstream LLM performance. We train TAPR using reinforcement learning with Group Relative Policy Optimization (GRPO), where rewards are derived from LLM-as-judge evaluations of both the reformulated prompt and the corresponding task output. Experimental results on diverse tasks, such as question answering, summarization, and arithmetic reasoning, show that our method yields consistent gains over base models in prompt rewriting ability. Fine-tuning Phi-4-mini-instruct (as the base model for TAPR) produces prompts that contain clearer and more instructive language, leading to higher accuracy on established benchmarks such as Natural Questions and GSM8K. Our code is available at: https://github.com/OliverSavolainen/task-specific-prompt-rewriter", "url": "https://wpnews.pro/news/tapr-enhancing-llm-performance-with-a-task-aware-prompt-rewriter", "canonical_source": "https://arxiv.org/abs/2607.28657", "published_at": "2026-08-03 04:00:00+00:00", "updated_at": "2026-08-03 04:12:43.198629+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "natural-language-processing", "ai-research"], "entities": ["TAPR", "Phi-4-mini-instruct", "Group Relative Policy Optimization", "Natural Questions", "GSM8K", "arXiv", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/tapr-enhancing-llm-performance-with-a-task-aware-prompt-rewriter", "markdown": "https://wpnews.pro/news/tapr-enhancing-llm-performance-with-a-task-aware-prompt-rewriter.md", "text": "https://wpnews.pro/news/tapr-enhancing-llm-performance-with-a-task-aware-prompt-rewriter.txt", "jsonld": "https://wpnews.pro/news/tapr-enhancing-llm-performance-with-a-task-aware-prompt-rewriter.jsonld"}}