3 papers
cs.LG2026
Reinforcement Learning with Backtracking Feedback
Bilgehan Sel, Vaishakh Keshava, Phillip Wallis +3
Addressing the critical need for robust safety in Large Language Models (LLMs), particularly against adversarial attacks and in-distribution errors, we introduce Reinforcement Lear…
cs.LG2026
Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks
Haoyu Liu, Dingcheng Li, Lukas Rutishauser +1
Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet their dual-stream architecture opens an u…
cs.LG2025
Adversarial Reinforcement Learning for Large Language Model Agent Safety
Zizhao Wang, Dingcheng Li, Vaishakh Keshava +4
Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, wh…