SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

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 optimization. To address this issue, we propose TACS, a trajectory-aware candidate selection framework

Read original source ↗ Open in workspace

recordType

paper

region

Global