AgentStripes: An Evidence-Graded Maturity Model for AI Agents

arXiv:2610.18603 · cs.AI, cs.CY, cs.SY, eess.SY · Submitted 2026-10-13 · Read on arXiv

cs.AI, cs.CY, cs.SY, eess.SY

Submitted: 2026-10-13

Updated: 2026-10-20

Comments: 32 pages, 7 figures, 4 tables, 116 references; supplementary information (15 pages, 8 figures, 21 tables) included in the same PDF. Code and data available on request

Code: https://github.com/naiknutan97/evidence-graded-age

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• AI Agents — 1× in this paper · explained in 2 episodes

Sources

• Governing the Agentic Enterprise: A Governance Maturity Model for Managing AI Agent Sprawl in Business Operations
• Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systems
• The AI Codebase Maturity Model: From Assisted Coding to Fully Autonomous Systems
• AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
• BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks
• Agentic AI in Industry: Adoption Level and Deployment Barriers
• $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
• NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls
• AgenTRIM: Tool Risk Mitigation for Agentic AI
• RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction
• WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
• ACEBench: Who Wins the Match Point in Tool Usage?
• AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
• The BrowserGym Ecosystem for Web Agent Research
• AURA: An Agent Autonomy Risk Assessment Framework
• AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
• SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
• AgentOps: Enabling Observability of LLM Agents
• WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
• MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark

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