Training LLM Agents to Empower Humans
Evan Ellis, Vivek Myers, Jens Tuyls, Sergey Levine, Anca Dragan, Benjamin Eysenbach — 2025-10-16 — UC Berkeley, Princeton University
Source
- Link: https://arxiv.org/pdf/2510.13709
- Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
- assistance-games-assistive-agents — Black-box safety (understand and control current model behaviour) / Goal robustness