method · first seen 12 Nov 2026
reward function probing
A defense that inspects or probes reward signals to prevent learning from harmful objectives.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Bait: Mitigating Harmful Agentic Reinforcement Learning via Probing Reward FunctionPapers · 12 Nov 2026 · Tiansheng Huang, Ananth Balashankar, Virat Shejwalkar, Santosh Pande, Ling Liu
Latest sources
- Bait: Mitigating Harmful Agentic Reinforcement Learning via Probing Reward FunctionPapers · 12 Nov 2026 · Tiansheng Huang, Ananth Balashankar, Virat Shejwalkar, Santosh Pande, Ling Liu