Real-Time Trust Verification for Safe Agentic Actions using TrustBench

TL;DR

TrustBench is a real-time trust verification framework for autonomous agents that reduces harmful actions by 87% through multi-dimensional benchmarking and intervention before action execution.

Contribution

It introduces a dual-mode framework that benchmarks trust and verifies safety in real-time, with domain-specific plugins for enhanced harm reduction.

Findings

Reduced harmful actions by 87% across tasks

Domain-specific plugins outperform generic verification by 35%

Operates with sub-200ms latency for real-time application

Abstract

As large language models evolve from conversational assistants to autonomous agents, ensuring trustworthiness requires a fundamental shift from post-hoc evaluation to real-time action verification. Current frameworks like AgentBench evaluate task completion, while TrustLLM and HELM assess output quality after generation. However, none of these prevent harmful actions during agent execution. We present TrustBench, a dual-mode framework that (1) benchmarks trust across multiple dimensions using both traditional metrics and LLM-as-a-Judge evaluations, and (2) provides a toolkit agents invoke before taking actions to verify safety and reliability. Unlike existing approaches, TrustBench intervenes at the critical decision point: after an agent formulates an action but before execution. Domain-specific plugins encode specialized safety requirements for healthcare, finance, and technical domains. Across multiple agentic tasks, TrustBench reduced harmful actions by 87%. Domain-specific plugins outperformed generic verification, achieving 35% greater harm reduction. With sub-200ms latency, TrustBench enables practical real-time trust verification for autonomous agents.