Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.16280v1 Announce Type: new Abstract: Before changing a deployed AI agent (a stricter safety gate, a new model), organizations must approve the change, starting from existing logs. Extendin...
arXiv:2610.16231v1 Announce Type: new Abstract: As large language models are increasingly adopted as multi-party communication facilitators, there is a growing demand for agents capable of balancing...
arXiv:2606.10173v2 Announce Type: replace-cross Abstract: On-device inference reduces exposure to remote infrastructure, but it does not establish privacy for an operating-system assistant that aggre...
arXiv:2607.02368v4 Announce Type: replace-cross Abstract: Researchers are increasingly prompting language models with cultural personas so that they answer questionnaires as diverse human groups woul...
arXiv:2610.15136v1 Announce Type: new Abstract: Trust calibration remains the dominant framing of AI-assisted decision making: the goal is to close the gap between perceived and actual trustworthines...
arXiv:2610.15191v1 Announce Type: new Abstract: Batch risk-based inspection scheduling struggles to detect a critical failure class: food facilities with recent clean inspections that subsequently de...
arXiv:2610.15322v2 Announce Type: new Abstract: Enabling the reuse and composition of knowledge and capabilities distributed across foundation models is an important step toward building scalable art...
arXiv:2610.14500v1 Announce Type: cross Abstract: Many widely used activation functions, including ReLU, GELU, Swish, and Sigmoid, produce predominantly positive outputs, resulting in a nonzero post-...
arXiv:2610.14530v1 Announce Type: cross Abstract: Multi-robot systems (MRS) offer significant advantages over single-robot platforms by enabling information sharing and coordination for different tas...
arXiv:2610.14852v1 Announce Type: cross Abstract: Reinforcement learning (RL) is promising for spatial text-to-image generation, but existing work largely focuses on policy optimization, assuming acc...
arXiv:2610.15282v1 Announce Type: cross Abstract: Large Language Models (LLMs) have made substantial progress in multilingual question answering, yet their ability to understand low-resource sociolin...
arXiv:2610.17382v1 Announce Type: cross Abstract: Score-based black-box adversarial attacks pose a serious threat to deployed machine learning systems by exploiting repeated model queries to craft ad...
arXiv:2610.17426v1 Announce Type: cross Abstract: Clinical decision-making is a sequential process of information collection, clinical inference, and forecasting under partial observability, often wi...
arXiv:2610.15681v1 Announce Type: cross Abstract: Parametric Computer-Aided-Design (CAD) modeling from human intent remains challenging, particularly during the conceptual design stage, where design...
arXiv:2610.20020v1 Announce Type: cross Abstract: It is folklore that passing "convergence" diagnostics does not guarantee that a Markov chain has converged. We prove this as an impossibility for any...
arXiv:2606.00797v2 Announce Type: replace-cross Abstract: Population-level heterogeneity is ubiquitous in biomedical data, where differences across demographic or clinical subgroups can substantially...
arXiv:2610.16881v1 Announce Type: new Abstract: There is a specific challenge designers face in developing autonomous robots capable of open-ended learning. This challenge is how one can develop such...
arXiv:2610.16838v1 Announce Type: new Abstract: As language-model agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central sa...
arXiv:2610.16426v1 Announce Type: new Abstract: Automated approval systems let coding agents execute high-risk actions with minimal human oversight by delegating the authorization decision to a class...
arXiv:2610.16042v1 Announce Type: cross Abstract: The increasing use of artificial intelligence (AI) in mental health applications raises concerns about its potential to internalize and perpetuate so...