TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization

Abstract

Gradient-based jailbreak suffix optimization methods typically update the suffix by retaining the candidate with the lowest current loss. We show that this seemingly natural design is fundamentally myopic: candidates that look better under the current-step proxy often fail to produce better jailbreak outcomes later in the search, revealing a form of selection-stage reward hacking. This suggests that candidate selection, rather than candidate generation alone, is a hidden bottleneck in suffix opt

Categories

Framework mappings

Suggested from the entry's categories.

@misc{xiao2026tacs,
  title = {{TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization}},
  author = {Shi-Liang Xiao},
  year = {2026},
  month = aug,
  eprint = {2608.29564},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/9f5d1542f077730ad7f968a1028ee7fc7cf9f544}
}