Are You Still the Agent I Authorized? Earned Authority under a Fixed Ceiling for Evolving Agents
Zhaoxi Zhang, Xiaomei Zhang
cs.AI, cs.CR
Submitted: 2026-07-26
Project page: https://www.nccoe.nist.gov/projects/software-and-ai-agent-identity-and-authorization
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
- Lifelong Learning of Large Language Model based Agents: A Roadmap
- Reflexion: Language Agents with Verbal Reinforcement Learning
- ExpeL: LLM Agents Are Experiential Learners
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Automated Design of Agentic Systems
- G\"odel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models
- Design Patterns for Securing LLM Agents against Prompt Injections
- Defeating Prompt Injections by Design
- On Safety Risks in Experience-Driven Self-Evolving Agents
- OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
- Dynamic Malicious Skills in Agentic AI
- From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
- Governing Dynamic Capabilities: Cryptographic Binding and Reproducibility Verification for AI Agent Tool Use
- Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization
- Progent: Securing AI Agents with Privilege Control
- Language-Based Agent Control
- SkillGuard: A Permission-Centric Framework for Agent Skill Security
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