Skip to content
AI News HubLIVE
Original source2 min read

TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter

Summary

Researchers introduce TAPR, a Task-Aware Prompt Rewriter trained with GRPO reinforcement learning to reformulate user prompts into task-optimized prompts that improve downstream LLM performance. Fine-tuning Phi-4-mini-instruct as the base model yields clearer, more instructive prompts and higher accuracy on benchmarks such as Natural Questions and GSM8K.

SourcearXiv AIAuthor: Oliver Savolainen, Emanuele Bastianelli, Hosein Azarbonyad
TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 17 Jul 2026]

Title:TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter

View a PDF of the paper titled TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter, by Oliver Savolainen and 2 other authors

View PDF HTML (experimental)

Abstract: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: this https URL

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2607.28657 [cs.AI]

(or arXiv:2607.28657v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2607.28657

arXiv-issued DOI via DataCite

Submission history

From: Hosein Azarbonyad [view email] [v1] Fri, 17 Jul 2026 15:37:07 UTC (4,618 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter, by Oliver Savolainen and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-07

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • TAPR reformulates user prompts into task-optimized prompts explicitly aimed at improving downstream LLM performance.
  • It is trained with GRPO, using LLM-as-judge rewards on both the rewritten prompt and the resulting task output.
  • Fine-tuning Phi-4-mini-instruct produces clearer prompts and accuracy gains on Natural Questions and GSM8K, with code released.

Highlights and analysis are generated automatically and may contain errors. Check the original source.