The paper investigates prompt minimization, aiming to reduce prompts to their smallest, most information-dense form without losing output fidelity. It argues that shorter prompts lower computational overhead and inference latency, especially when large contexts are unnecessarily included, and that longer prompts can harm LLM reasoning and accuracy. The authors propose three frameworks to identify minimal prompts and show that these often produce outputs comparable to longer versions, highlighting redundancy in the input space and opening new avenues for efficient prompt engineering.
By Marius F. R. Juston, Kevin A. Karim, Jonathan Gao, Kevin C. Li, Rudhi Bashambu
The paper investigates how small lexical changes in prompts can cause large performance swings in large language models. Using a dataset of 132,000 prompt variants, the authors uncover a scaling law linking higher average task performance to lower variance and greater robustness. They identify domain-specific terminology and explicit action directives as key linguistic factors that stabilize prompts, and propose an automated Prompt-Refining Agent that reduces performance variance by 40.7% in code generation while maintaining or improving mean performance.
By Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu
arXiv:2609.23716v1 Announce Type: cross
Abstract: Textual-gradient methods automate prompt optimization through natural-language feedback, but their iterative updates can be unstable. We identify two...
By Yifan Xu, Yixuan Li, Xinzhuo Li, Yixin Gu, Yifan Shen, Lijun Yu, Haohan Wang
Instruction-following ability is critical for deploying large language models in real-world applications, where downstream components depend on the output satisfying specific constraints. Modern deployments increasingly handle the full task in a single LLM call, with one prompt specifying a layered output whose overall artifact, structural sections, and nested fields must each satisfy concrete constraints.
arXiv:2607. 02854v1 Announce Type: cross Abstract: Before fixing an issue, it is useful to first reproduce it by generating a bug reproduction test (BRT).
By Toufique Ahmed, Jatin Ganhotra, Avraham Shinnar, Martin Hirzel
arXiv:2606. 17164v1 Announce Type: cross Abstract: Prompting has become the primary interface between humans and generative AI, yet many natural language prompts remain fragile: roles, goals, constraints, and expected outputs are often buried in prose or left implicit.
By Enkhzol Dovdon
arXiv:2605. 11599v3 Announce Type: replace Abstract: Fixed reasoning benchmarks evaluate canonical prompts, but semantically valid changes in presentation can still change model behavior.
By Hongmin Li
arXiv:2606. 11459v1 Announce Type: cross Abstract: Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential.
By Fei Wang, Si Si, Cho-Jui Hsieh, Inderjit S. Dhillon
The behavior of contemporary generative Large Language Models (LLMs) is directly shaped by prompts, unstructured texts that describe the desired output and model behavior. In this paper we argue that prompts are linguistic objects that merit investigation in their own right.
arXiv:2607. 09175v1 Announce Type: new Abstract: Deployed LLM agents rely on agentic context, the model-external textual control content assembled by an operational harness.
By Dan C. Hsu, Luke Lu
arXiv:2606. 07548v1 Announce Type: cross Abstract: The MedHopQA challenge presents a critical test for Large Language Models (LLMs): complex, multi-hop reasoning in the high-stakes biomedical domain.
By Ahmed Bajaber, Mohammed Alliheedi