The Irreversibility Budget: Fleet-Level Risk Accounting and Admission Control for Agent Operating Systems
cs.AI, cs.DC, cs.OS
Submitted: 2026-08-31
Updated: 2026-08-31
Code: https://github.com/mpi-dsg/irreversibility-budget
Terminology
Sources
- Insuring Every Action: An Authority Frontier Framework for Runtime Actuarial Control of Autonomous AI Agents
- Cordon: Semantic Transactions for Tool-Using LLM Agents
- Quantifying Trust: Financial Risk Management for Trustworthy AI Agents
- AIOS: LLM Agent Operating System
- Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
- MemGPT: Towards LLMs as Operating Systems
- The Controllability Trap: A Governance Framework for Military AI Agents
- When Agent Automation Becomes Profitable: Quantifying and Insuring Autonomous AI Risk through Trace-Economic Underwriting
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
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