Frank Xiao

Identifiers

• name variant Frank Xiao 0.60 · backfill

Papers (4)

1. Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization cs.LG · 2026 · author #1
2. Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents cs.LG · 2026 · author #1
3. Probe-Based Data Attribution: Discovering and Mitigating Undesirable Behaviors in LLM Post-Training cs.LG · 2026 · author #1
4. Why Do Language Model Agents Whistleblow? cs.LG · 2025 · author #2

Mentions

• 2606.12016 #1 · arxiv_oai · confidence 0.70 Frank Xiao
• 2606.11998 #1 · arxiv_oai · confidence 0.70 Frank Xiao

Frequent Coauthors

• Mary Phuong 2 shared papers
• Asa Cooper Stickland 1 shared papers
• Guido Bergman 1 shared papers
• Kushal Agrawal 1 shared papers
• Santiago Aranguri 1 shared papers