Itay Nakash
4 papers · 2025–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
model evaluation
(1)
bias detection
(1)
adversarial attack
(1)
autonomous agent
(1)
multi-turn interaction
(1)
agent evaluation
(1)
prompt injection
(1)
llm agent
(1)
security vulnerability
(1)
indirect attack
(1)
react agent
(1)
agent safety
(1)
foot-in-the-door attack
(1)
large language model
(1)
reasoning agent
(1)
multi-agent system
(1)
user simulation
(1)
test-time compute
(1)
jailbreak prevention
(1)
policy adherence
(1)
Papers
Efficient Agent Evaluation via Diversity-Guided User Simulation
ACL 2026
Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In
NAACL 2025
Effective Red-Teaming of Policy-Adherent Agents
EMNLP 2025
Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models
ACL 2025