Madhulika Srikumar et al., Partnership on AI
researchactive

Prioritizing Real-Time Failure Detection in AI Agents

Madhulika Srikumar et al., Partnership on AI

View original resource

Partnership on AI paper arguing offline evaluation is insufficient and detailing methods for real-time failure detection in deployed agents - anomaly scoring on trajectories, tool-call validation, and escalation triggers. Includes recommendations for deployers and auditors.

Tags

agentic AIevaluation

At a glance

Published

2025

Jurisdiction

International

Category

Evaluation and benchmarks

Access

Public access

More in Evaluation and benchmarks

tau-bench: A benchmark for tool-agent-user interaction

Sierra Research • 2024

SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Jimenez et al. (Princeton) • 2023

WebArena: A Realistic Web Environment for Building Autonomous Agents

Zhou et al. • 2023

Related resources

Practices for governing agentic AI systems: OpenAI's seven safety principles

Governance frameworks • OpenAI

Taxonomy of Failure Mode in Agentic AI Systems

Risk taxonomies • Microsoft

EleutherAI LM Evaluation Harness

Assessment and evaluation • EleutherAI

Build your AI governance program

VerifyWise helps you implement AI governance frameworks, track compliance, and manage risk across your AI systems.

Explore the libraryStart free trial
Prioritizing Real-Time Failure Detection in AI Agents | VerifyWise AI Governance Library