Pith. sign in

Rodriguez-Aguilar, and Carles Sierra

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.LG 1

years

2026 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Multi-Agent AI Safety as an Institutional Design Problem

cs.LG · 2026-08-10 · conditional · novelty 6.0

In synthetic delegation workflows, identical final violation rates hide different mechanisms: prompts prevent prohibited attempts, provenance-aware guards block and recover, and a local policy guard fails when transformations rewrite visible policy.

citing papers explorer

Showing 1 of 1 citing paper.

  • Multi-Agent AI Safety as an Institutional Design Problem cs.LG · 2026-08-10 · conditional · none · ref 5

    In synthetic delegation workflows, identical final violation rates hide different mechanisms: prompts prevent prohibited attempts, provenance-aware guards block and recover, and a local policy guard fails when transformations rewrite visible policy.