This work developed AgentInspect, a framework that automatically detects six types of behavioral failures in LangChain-based AI agents by analyzing their execution trajectories across three evaluation settings: a baseline setting using real tool responses, a simulated setting incorporating synthetic tool responses, and a hybrid setting that combines the real and simulated tool responses.
This work presents ATLAS (Automata Learning for Agent Trajectory Analysis and Strategy Discovery), an approach for recovering interpretable behavioral models from agent trajectories that enable systematic understanding and analysis of otherwise opaque AI agents.
Ignacio D. Lopez-Miguel, A. Happe, Jürgen Cito et al.· Proceedings of the ACM/IEEE...· 0 citations
With the proliferation of LLM agents, the ability to understand and diagnose failures in agents is essential to achieving superior effectiveness and trustworthiness. As agent failures often manifest via long and complex trajectories, manually finding the needles in the haystack is untenable. However, traditional diagnosis techniques for software bugs can hardly address LLM agent failures, while completely relying on LLMs as the judge yields unreliable diagnosis results. To overcome these challenges, this paper presents AGENTSCOPE, a new neuro-symbolic approach for agent failure mode diagnosis. The key principle of AGENTSCOPE is to abstract agent behavior, based on its trajectories, into structured representations. Furthermore, AGENTSCOPE introduces the concept of neural invariants to specify agent behavior properties. AGENTSCOPE leverages LLM-guided reasoning atop the structured representation against neural invariants to pinpoint both the failure step and its type in the trajectory. We show the effectiveness of AGENTSCOPE on publicly available agent failure datasets (Who&When) and a more comprehensive dataset created by us (AgentErrata), where AGENTSCOPE significantly outperforms the current state of the art in fault localization and attribution accuracy. Our work shows that integrating structured abstractions with LLM-guided reasoning enables effective, reliable, and interpretable diagnosis for agent failures.
Jia-Yi Bi, Yanjie Gao, Yuan-Min Xie et al.· 0 citations
We propose a formal model for testing AI agents in stateful environments, using Finite State Machine (FSM) semantics to enable deterministic, trace-level evaluation via an explicit test oracle. Our approach introduces a classified action alphabet and six computable failure-mode detectors for automatic analysis over agent traces. Applying this methodology to 350 multi-turn network configuration runs, we find that aggregate scores often miss structural failures revealed by trajectory analysis, and that meltdown rates alone fail to distinguish distinct failure mechanisms. Agents satisfy locally verifiable intent properties more than twice as often as remotely verifiable ones, exposing a critical awareness–action gap (the difference in satisfaction rate between local and remote evidence). Trajectory-level analysis is therefore essential for robust evaluation of autonomous agents in complex systems.
Ahmed Twabi, Yepeng Ding, Tohru Kondo· International Conference on...· 0 citations
AI Agents are increasingly deployed in real-world settings, where they interact with external tools and make sequential decisions with limited human oversight. This creates a pressing need for reliable and auditable explanations of what an agent did and why. However, traditional Explainable AI (XAI) methods fall short of providing the process-level transparency required for such interactive, multi-step systems, motivating a paradigm shift toward approaches specifically designed for AI Agents. To address this gap, we present a post-hoc XAI framework that transforms a lengthy agent's execution trace into a structured report and a faithful natural-language explanation explicitly grounded in its observable behavior. Because it relies solely on execution traces, the framework applies across different agent architectures, environments, and tasks. Human and automated evaluations across multiple benchmarks and architectures show that our framework produces high-quality, trace-faithful explanations while reliably identifying unsupported claims, unjustified actions, and evidence gaps, outperforming naive LLM-generated explanations.
Vittoria Vineis, Fabiano Veglianti, Lorenzo Antonelli et al.· 0 citations
This survey synthesizes 257 papers spanning agent evaluation, software assurance, cyber-physical systems, runtime monitoring, and regulatory guidance in order to characterize the validation problem for agentic systems, and concludes with a lifecycle-oriented research agenda centered on bounded-autonomy specifications, adversarial trajectory generation, runtime monitoring, and audit-ready evidence structures.
Fabio Orazio Mirto, L. D’Agati, Giuseppe Tricomi et al.· arXiv.org· 0 citations
AEROBAT is introduced, the first multi-agent system to automate behavioral scientific research on AI agents and demonstrates that automated behavioral scientific research on AI agents can complement and extend the reach of manual research.
S. Lee, Jongha Lee, Jaewan Chun et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
