Andy Luo
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1NLP×1ML×1
Frequent co-authors
Research Timeline
2026
Adaptive Instruction Composition for Automated LLM Red-Teaming
The paper introduces Adaptive Instruction Composition, a novel framework that uses reinforcement learning to intelligently combine crowdsourced texts, significantly improving the effectiveness and diversity of LLM red-teaming attacks compared to random methods.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIcs.CLRecentApr 22, 2026
Adaptive Instruction Composition for Automated LLM Red-Teaming
Jesse Zymet, Andy Luo, Swapnil Shinde, Sahil Wadhwa +1 more
The paper introduces Adaptive Instruction Composition, a novel framework that uses reinforcement learning to intelligently combine crowdsourced texts, significantly improving the effectiveness and div…
View →