2 papers
cs.LG2026
Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience
Zixuan Wang, Hao Li, Fengyu Gao +5
Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vulnerable to prompt injection a…
cs.LG2026
DUET: Co-Evolving Solver and Grader Agents
Fengyu Gao, Sourav Pal, Austin Z. Henley +2
Agentic workflows are increasingly used across domains such as technology, finance, and enterprise operations. As these agents become more widely deployed, continually improving th…