TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization

Abstract

Discrete text-trigger optimization -- searching for text sequences that, when ingested by a model, steer it toward a specified objective -- underpins model red-teaming (e.g., LLM jailbreaks), as well as auditing and interpretability. However, the current state of discrete optimizers hinders their adoption and progress. First, existing optimizers, when open-sourced at all, are scattered across research codebases tied to specific models, objectives, and problem domains. Second, optimizer variants

Categories

Framework mappings

Suggested from the entry's categories.

@misc{bentov2026tropt,
  title = {{TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization}},
  author = {Matan Ben-Tov and Mahmood Sharif},
  year = {2026},
  month = jun,
  eprint = {2606.23496},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.23496}
}