Related papers: Executor-Side Progressive Risk-Gated Actuation for…
A policy-governed RAG architecture is specified for audit-ready generation in regulated workflows, organized as a triptych: (I) Contracts/Control (SHRDLU-like), which governs output adherence to legal and internal policies; (II)…
Action-feedback delay during operation reduces both task performance and sense of agency (SoA). In this study, using information-theoretic free energy, we formalized a novel mathematical model for explaining the influence of delay on both…
Intent-Based Networking (IBN) simplifies network management, but its reliability is challenged by "intent drift", where the network's state gradually deviates from its intended goal, often leading to silent failures. Conventional approaches…
Agentic AIs $-$ AIs that are capable and permitted to undertake complex actions with little supervision $-$ mark a new frontier in AI capabilities and raise new questions about how to safely create and align such systems with users,…
Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sample throughput, limiting the benefit of search; (2) a generalization gap where…
Large language models (LLMs) deployed behind APIs and retrieval-augmented generation (RAG) stacks are vulnerable to prompt injection attacks that may override system policies, subvert intended behavior, and induce unsafe outputs. Existing…
The emergence and growth of 5G and beyond 5G (B5G) networks has brought about the rise of so-called ''programmable'' networks, i.e., networks whose operational requirements are so stringent that they can only be met in an automated manner,…
LoRa is a promising technology in the current Internet of Things market, which operates in un-licensed bands achieving long-range communications and with ultra power devices. In this work we capitalize on the idea introduced in [1], i.e.…
Probabilistic security assessment and real-time dynamic security assessments (DSA) are promising to better handle the risks of system operations. The current methodologies of security assessments may require many time-domain simulations for…
In this article, we propose a backpropagation-free approach to robotic control through the neuro-cognitive computational framework of neural generative coding (NGC), designing an agent built completely from powerful predictive…
We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commit to a wrong approach early and exhaust the step budget, the post-failure trajectory contains the…
Artificial intelligence (AI) agents are increasingly used in a variety of domains to automate tasks, interact with users, and make decisions based on data inputs. Ensuring that AI agents perform only authorized actions and handle inputs…
Enterprise AI systems increasingly deploy multiple intelligent agents across mission-critical workflows that must satisfy hard policy constraints, bounded risk exposure, and comprehensive auditability (SOX, HIPAA, GDPR). Existing…
AI-assisted software generation has increased development speed, but it has also amplified a persistent engineering problem: systems that are functionally correct may still be structurally insecure. In practice, prompt-based security review…
Internet of Things (IoT) platforms with trigger-action capability allow event conditions to trigger actions in IoT devices autonomously by creating a chain of interactions. Adversaries exploit this chain of interactions to maliciously…
GUI Process Automation (GPA) is a lightweight but general vision-based Robotic Process Automation (RPA), which enables fast and stable process replay with only a single demo. Addressing the fragility of traditional RPA and the…
Group-relative RL training (GRPO) samples a small group of parallel rollouts for every training prompt and uses their within-group reward spread to compute per-trajectory advantages. In agentic environments each rollout is a long multi-turn…
AI agents execute tens to hundreds of chained LLM calls per task, yet GPU schedulers treat each call as independent, discarding gigabytes of intermediate state between steps and inflating end-to-end latency by 3-8x. We argue that this…
Frontier AI developers may fail to align or control highly-capable AI agents. In many cases, it could be useful to have emergency shutdown mechanisms which effectively prevent misaligned agents from carrying out harmful actions in the…
As multi-agent systems move from short interactions to tool-using workflows with specialized roles and persistent state, completion becomes a runtime-control problem rather than a purely generative one. This preprint studies verify-gated…