Pith. sign in

Agentguardian: Learning access control policies to govern AI agent behavior.CoRR, abs/2601.10440, 2026

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

2026 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

SafeCommit: Certifying When Memory-Grounded Agents May Safely Act

cs.AI · 2026-08-04 · conditional · novelty 6.0

SafeCommit introduces a calibrated plausible-world certificate gate that releases a side-effectful agent action only when it is safe in every retained world, bounding unsafe commits at a user-chosen risk level alpha.

citing papers explorer

Showing 1 of 1 citing paper.

  • SafeCommit: Certifying When Memory-Grounded Agents May Safely Act cs.AI · 2026-08-04 · conditional · none · ref 1

    SafeCommit introduces a calibrated plausible-world certificate gate that releases a side-effectful agent action only when it is safe in every retained world, bounding unsafe commits at a user-chosen risk level alpha.