Does Moral Reasoning Training Help or Hurt? Red-Teaming RL-Trained Ethical Agents with Persona Attacks
This story is from 2026-09-17. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.17552v1 Announce Type: new Abstract: Moral-reward RL can make language-model agents more cooperative, but whether that alignment survives adversarial persona pressure is unknown. Such attacks are realistic: retrieved context, tool outputs, or multi-turn framing can all inject role instru…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-09-17 04:00 · arXiv cs.CL
Does Moral Reasoning Training Help or Hurt? Red-Teaming RL-Trained Ethical Agents with Persona Attacks