arXiv:2606. 13621v1 Announce Type: new Abstract: Shielded reinforcement learning is typically presented as a runtime safety mechanism that compiles temporal-logic specifications into automata restricting an agent's actions.
Shielded reinforcement learning is typically presented as a runtime safety mechanism that compiles temporal-logic specifications into automata restricting an agent's actions. We argue this is the wrong product.
arXiv:2606. 26057v1 Announce Type: cross Abstract: AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems.
arXiv:2606. 14130v1 Announce Type: new Abstract: Safe coordination problems surface in multi-agent reinforcement learning when global safety cannot be enforced by any agent unilaterally: the admissibility of one agent's action may depend on the dynamics of other agents.
arXiv:2506. 07468v4 Announce Type: replace Abstract: Conventional large language model (LLM) safety alignment relies on a reactive, disjoint loop: attackers exploit a static model, then defenders patch exposed vulnerabilities.
arXiv:2608. 03662v1 Announce Type: new Abstract: Safety shields are runtime enforcement mechanisms that restrict the actions of a controller to guarantee safety.
arXiv:2601. 09923v3 Announce Type: replace Abstract: AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior.
arXiv:2510. 06445v3 Announce Type: replace-cross Abstract: LLM-based agents are now used throughout cybersecurity.
arXiv:2606. 03804v1 Announce Type: new Abstract: Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their environment.
arXiv:2608. 11274v1 Announce Type: cross Abstract: The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI.
arXiv:2607. 03423v1 Announce Type: cross Abstract: Modern AI agent implementations such as frontier coding agents chain multiple tools at runtime that create a security surface that per-tool guardrails are unable to address, as individually permitted tools can violate organizational policies when composed.
arXiv:2607. 15003v1 Announce Type: new Abstract: The deployment of autonomous cyber-physical systems in safety-critical environments requires closed-loop control strategies (i.
arXiv:2607. 04613v1 Announce Type: new Abstract: Autonomous agents are moving from sandboxed text generators to operators of code, data, and physical infrastructure, and they increasingly learn while deployed.