Willful Disobedience: Automatically Detecting Failures in Agentic Traces

Abstract

AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make validation difficult. Outcome-only benchmarks can miss critical procedural failures, such as incorrect workflow routing, unsafe tool usage, or violations of prompt-specified rules. This paper presents AgentPex, an AI-powered tool designed to systematically evaluate agentic traces. AgentPex extracts behavioral rules from agent prompts and system instructions, then uses these specifications to automatically evaluate traces for compliance. We evaluate AgentPex on 424 traces from τ2-bench across models in telecom, retail, and airline customer service. Our results show that AgentPex distinguishes agent behavior across models and surfaces specification violations that are not captured by outcome-only scoring. It also provides fine-grained analysis by domain and metric, enabling developers to understand agent strengths and weaknesses at scale.

Figures (9)

• Figure 1: The agent reaches the correct final outcome but violates the transition, output, and predicted-plan specifications. AgentPex flags these violations.
• Figure 2: Extracted output and transition rules (subset) for the airline-agent trace.
• Figure 3: The AgentPex pipeline from raw trace import through specification extraction to evaluation and aggregate scoring.
• Figure 4: Example extracted rules per specification type from the airline-agent trace.
• Figure 5: Traces sorted by AgentPex aggregate (low to high) alongside the $\tau^2$ composite score. Low-$\tau^2$ traces concentrate among low AgentPex scores, showing agreement without ground truth.