Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.22790v1 Announce Type: new Abstract: Undergraduate programmes in intelligent medical engineering are expanding, yet laboratory curricula lag behind the multimodal, long-tailed, and distrib...
arXiv:2609.23640v1 Announce Type: new Abstract: Human-feedback alignment has made language models useful assistants and is commonly described as aligning them with humans. However, the responses peop...
arXiv:2609.24165v1 Announce Type: new Abstract: Synchrotron data reduction, detector calibration followed by azimuthal integration of terabyte-scale diffraction series, is a multi-step, expert-bound...
arXiv:2609.22664v1 Announce Type: cross Abstract: Research on large language model agents for penetration testing is evaluated almost entirely by capability: whether the agent captures a flag or repr...
arXiv:2609.22724v1 Announce Type: cross Abstract: Mobile agents powered by foundation models now automate complex, multi-step workflows on real devices, but their trajectories can violate app-specifi...
arXiv:2609.22961v1 Announce Type: cross Abstract: Agentic systems increasingly invoke tools, services, data, and other agents across organizational boundaries, yet a relying party cannot assess a del...
arXiv:2609.22981v1 Announce Type: cross Abstract: We present a dual-locking method for securing trained neural networks that combines key-driven index permutation with PIN-based watermarking based on...
arXiv:2609.23894v1 Announce Type: cross Abstract: Agentic AI extends LLM security beyond generated content to persistent state, autonomous actions, tool use, and interactions with humans and other ag...
arXiv:2609.24669v1 Announce Type: cross Abstract: Providing autonomous intelligence, pervasive connectivity and usability to human life and industry has led to the emergence of the Internet of Things...
arXiv:2602.20628v2 Announce Type: replace Abstract: AIs are increasingly being deployed with greater autonomy and capabilities, which increases the risk that a misaligned AI may be able to cause cata...
arXiv:2509.26200v2 Announce Type: replace-cross Abstract: Agentic artificial intelligence is a candidate enabler of Level-4 autonomy in sixth-generation (6G) networks, but agents reasoning over a sha...
arXiv:2605.02346v2 Announce Type: replace-cross Abstract: Operational technology (OT) devices run safety-critical physical processes, yet their security testing remains manual and expert-intensive. A...
arXiv:2609.25021v1 Announce Type: new Abstract: Large Language Models (LLMs) tend to add disclaimers like "I'm just an AI" when asked about something related to themselves. The self-reports from such...
arXiv:2609.25297v1 Announce Type: new Abstract: Prioritized experience replay (PER) improves sample efficiency by replaying high-priority transitions, usually according to absolute temporal-differenc...
arXiv:2609.25373v1 Announce Type: new Abstract: On-device assistants require function-calling models that map natural language to local system actions, but existing resources emphasize web APIs or na...
arXiv:2609.25634v1 Announce Type: new Abstract: We trained 64 independently seeded networks in four configurations, continuing each to sustained convergence or a 40,000-epoch ceiling. We then asked w...
arXiv:2609.25692v1 Announce Type: new Abstract: Graph domain adaptation (GDA) transfers knowledge from a labeled source graph to an unlabeled target graph under shifts in both node attributes and gra...
arXiv:2609.25735v1 Announce Type: new Abstract: Class-balanced replay controls class frequency but does not determine the interval between successive replay appearances of a class. We study this inte...
arXiv:2609.26112v1 Announce Type: new Abstract: Mechanistic interpretability reverse-engineers transformer circuits one input at a time, leaving observed mechanisms without guarantees over bounded in...
arXiv:2609.26257v1 Announce Type: new Abstract: Continual learning (CL) aims to incrementally acquire knowledge from sequential data while avoiding catastrophic forgetting. Recently, prompt tuning ha...