Beyond Component Testing: Validating Agentic AI Systems

arXiv:2607.29405 · cs.AI, cs.MA, cs.SE · Submitted 2026-07-31 · Read on arXiv

cs.AI, cs.MA, cs.SE

Submitted: 2026-07-31

Updated: 2026-10-08

Code: https://github.com/ProSoDiAC/agentic-ai-validation-mapping-study

Terminology

• Agentic AI — 3× in this paper · explained in 1 episode
• Agentic AI systems — 2× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Papers — 1× in this paper · explained in 3 episodes

Sources

• Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systems
• Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions
• Concrete Problems in AI Safety
• AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
• A Run on Fossil Fuel? Climate Change and Transition Risk
• SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
• Assurance 2.0: A Manifesto
• Why Do Multi-Agent LLM Systems Fail?
• Decentralized Governance of Autonomous AI Agents
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
• Reactive Multi-agent Coordination using Auction-based Task Allocation and Behavior Trees
• AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
• Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
• Effective Strategies for Asynchronous Software Engineering Agents
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
• Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)
• AI safety via debate
• ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks
• Limits to Verification and Validation of Agentic Behavior
• Language Models (Mostly) Know What They Know

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems