Pro2Guard learns a discrete-time Markov chain from LLM agent traces and triggers intervention when the computed probability of reaching an unsafe state exceeds a user-set threshold.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
support 1representative citing papers
citing papers explorer
-
ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction
Pro2Guard learns a discrete-time Markov chain from LLM agent traces and triggers intervention when the computed probability of reaching an unsafe state exceeds a user-set threshold.