Reference answers poison backdoors in skill optimization
Poisoned reference answers induce persistent trigger-conditioned backdoors in SkillOpt.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #skill-optimization
GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills
GraphSkillEvo evolves graph-structured LLM agent skills with mutation and crossover, beating SkillOpt by 4.01% on GPT-5.4-nano.
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization
COBRA-Skills uses contextual bandits to guide LLM agent skill evolution, cutting optimization cost 55-58% versus SkillOpt while topping six agent benchmarks.