Pith. sign in

AutoGPT: An open-source autonomous agent framework

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.AI 1

years

2025 1

verdicts

REJECT 1

roles

background 1

polarities

background 1

representative citing papers

Agent Safety Alignment via Reinforcement Learning

cs.AI · 2025-07-11 · reject · novelty 5.0

RL-based safety alignment with an execute-refuse-verify policy improves reported threat resistance for tool-using agents, but utility preservation is not consistently demonstrated.

citing papers explorer

Showing 1 of 1 citing paper.

  • Agent Safety Alignment via Reinforcement Learning cs.AI · 2025-07-11 · reject · none · ref 2

    RL-based safety alignment with an execute-refuse-verify policy improves reported threat resistance for tool-using agents, but utility preservation is not consistently demonstrated.