Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2602. 14095v2 Announce Type: replace Abstract: Monitoring chain-of-thought (CoT) reasoning is a foundational safety technique for large language model agents; however, this oversight is compromised if models learn to conceal their reasoning.
arXiv:2607. 04389v1 Announce Type: new Abstract: It is increasingly common to aggregate predictions from multiple LLMs, each with domain expertise or access to private tools and data, to improve collective prediction performance.
arXiv:2607. 02567v1 Announce Type: cross Abstract: Radio frequency fingerprint identification (RFFI) provides a physical-layer credential for Internet of Things devices, but open-set decisions become fragile when a threshold calibrated on a source receiver is transferred to a target receiver.
arXiv:2607. 04072v1 Announce Type: cross Abstract: Large language models can generate plausible quantum code, but it is unclear whether they can reliably target the specific software development kit (SDK) version requested by the user.
arXiv:2607. 02944v1 Announce Type: cross Abstract: We propose PRECEDE, a precedent-guided co-scientist for side-effect-aware drug redesign that revises a parent compound to mitigate a specified side effect while preserving therapeutic function.
arXiv:2601. 11960v3 Announce Type: replace-cross Abstract: Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide with the one producing inference responses.
arXiv:2607. 02586v1 Announce Type: new Abstract: Governance frameworks ask AI providers and auditors for documented evaluation evidence, and perturbation-based construct-validity audits are a common form of that evidence.
arXiv:2607. 05251v1 Announce Type: cross Abstract: Neural network verification and data privacy are inherently in tension: verification demands full access to model parameters and input data, yet both are increasingly restricted by privacy regulations and intellectual property constraints.
arXiv:2606. 05242v2 Announce Type: replace-cross Abstract: Stochastic gradient Langevin algorithms often use tamed denominators to stabilize superlinear drifts.
arXiv:2509. 22082v3 Announce Type: replace Abstract: Federated learning enables distributed information sharing and collaborative model training without exposing raw client data.
arXiv:2607. 03770v1 Announce Type: cross Abstract: Prior studies have demonstrated that diffusion classifiers achieve robust zero-shot classification performance.
arXiv:2607. 04293v1 Announce Type: cross Abstract: Building AI Scientist agents with Large Language Models (LLMs) has recently attracted growing attention.
arXiv:2607. 05281v1 Announce Type: cross Abstract: Present-day quantum computing is cloud-based, where a user submits a circuit to a service provider's proprietary backend hardware.
arXiv:2509. 17255v2 Announce Type: replace-cross Abstract: We present the first language-model-driven agentic artificial intelligence (AI) system to autonomously execute multi-stage physics experiments on a production synchrotron light source.
arXiv:2607. 05242v1 Announce Type: cross Abstract: Personalized incentive allocation is vital for e-commerce, where uplift modeling is the standard for estimating Individual Treatment Effects (ITE).
arXiv:2607. 03847v1 Announce Type: new Abstract: Understanding why discovered scenarios become critical in scenario-based testing is essential for effectively leveraging them in decision-making systems.
arXiv:2607. 03624v1 Announce Type: cross Abstract: This paper challenges the assumption that vision-language models (VLMs) require fixed patch-based 2D vision features.
arXiv:2605. 16103v2 Announce Type: replace Abstract: Q-learning is known to suffer from overestimation bias: because the Bellman update maximizes noisy or imperfect action-value estimates, positive errors can be selected and propagated, causing learned values to exceed the true optimal values.
arXiv:2601. 18253v2 Announce Type: replace-cross Abstract: Accurate evaluation of user satisfaction is critical for iterative development of conversational AI.
arXiv:2604. 23270v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs).