Who Holds the Pen? Let Specifications, Not Agents, Sign Off

arXiv:2609.29921 · cs.AI, cs.MA · Submitted 2026-09-24 · Read on arXiv

cs.AI, cs.MA

Submitted: 2026-09-24

Updated: 2026-09-24

Terminology

• Verification — 23× in this paper · explained in 2 episodes
• Benchmark — 17× in this paper · explained in 2 episodes
• Verifier — 17× in this paper · explained in 2 episodes
• Trace — 12× in this paper · explained in 2 episodes
• Adaptation — 6× in this paper · explained in 1 episode
• Alignment — 4× in this paper · explained in 1 episode
• Provenance — 4× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Abstention — 3× in this paper · explained in 1 episode
• Post-Selection — 3× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Agent Skills — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Admissibility — 1× in this paper · explained in 2 episodes
• Agentic System — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Multi-Agent System — 1× in this paper · explained in 5 episodes
• Structural Constraints — 1× in this paper · explained in 2 episodes

Sources

• Constitutional AI: Harmlessness from AI Feedback
• MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers
• AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
• AgentOps: Enabling Observability of LLM Agents
• Consensus on Transaction Commit
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills
• Cryptographic Runtime Governance for Autonomous AI Systems: The Aegis Architecture for Verifiable Policy Enforcement
• Verify-Gated Completion as Admission Control in a Governed Multi-Agent Runtime: A Bounded Architecture Case Study
• Training language models to follow instructions with human feedback
• Formal Policy Enforcement for Real-World Agentic Systems
• Neuro-Symbolic Verification on Instruction Following of LLMs
• Verification-Gated Agentic Mission-State Governance for Intelligent Industrial Multi-Robot Systems
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• GLM-5: from Vibe Coding to Agentic Engineering

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection