Metraipolis › archive › dc_349c07f8eeeb

Prompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity — arXiv:2609.31505

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31505
License (as archived)
CC0-1.0
Archived
2026-10-08T01:38:44.138Z
SHA-256 of the archived text
27ac26e05fef10edab5729b828a39766a48d33a6801a13ea156c30379d26ed84
Stable URL of this page
https://metraipolis.com/documento/dc_349c07f8eeeb

How to cite

Prompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity — arXiv:2609.31505 — arXiv (en), https://arxiv.org/abs/2609.31505 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_349c07f8eeeb (Metraipolis archive dc_349c07f8eeeb, sha256 27ac26e05fef10edab5729b828a39766a48d33a6801a13ea156c30379d26ed84)
BibTeX
@misc{dc349c07f8eeeb,
  title = {Prompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity — arXiv:2609.31505},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31505},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_349c07f8eeeb; sha256 27ac26e05fef10edab5729b828a39766a48d33a6801a13ea156c30379d26ed84},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31505. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Despite the growing capabilities of large language models (LLMs), prompt design remains largely heuristic and ad hoc. This project will explore $\textit{prompt minimization}$, the process of reducing prompts to their smallest, most information-dense form while preserving output fidelity. Practically, shorter prompts reduce computational overhead and inference latency, especially when large contexts, such as entire documents or codebases, are included unnecessarily. Further, longer prompts can damage LLM reasoning and accuracy. Theoretically, the existence of multiple prompts yielding equivalent outputs suggests a high degree of redundancy in the input space, raising fundamental questions about what information is essential to elicit specific model behaviors. We propose three variant frameworks to identify and evaluate minimal prompts and demonstrate that minimal prompts often produce outputs comparable to those of their longer counterparts. These findings suggest new directions for efficient prompt engineering and deepen our understanding of input compression in LLMs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.31505 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T01:12:14.388Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).