Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 22563v1 Announce Type: new Abstract: Industrial agent benchmarks require realistic evaluation scenarios that integrate telemetry, failure modes, maintenance records, and domain standards.
arXiv:2607. 24604v1 Announce Type: cross Abstract: Generate--test--revise loops are common in coding agents, but repetition alone provides no reliability guarantee.
arXiv:2602. 01348v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) can achieve strong answer accuracy on multi-hop questions, but outcome-level rewards often leave reasoning traces weakly grounded and difficult to audit.
arXiv:2605. 12759v2 Announce Type: replace Abstract: The Lightning Network (LN) is a second-layer protocol for Bitcoin designed to enable fast and cost-efficient off-chain transactions.
arXiv:2502. 04678v2 Announce Type: replace Abstract: Repeated first-price auctions are contextual decision problems with censored but reusable feedback: after submitting a bid, a learner can infer the outcomes of related bids and evaluate them under different private values.
arXiv:2607. 24025v1 Announce Type: cross Abstract: Transformer architectures have achieved remarkable success across diverse domains; however, directly applying their standard self-attention mechanism to recommendation often yields suboptimal performance, sometimes even trailing behind well-designed simple recommendation models.
arXiv:2607. 23883v1 Announce Type: cross Abstract: In this paper, we examine the difficulties of using standard techniques for medical image classification due to long-tailed distributions (wherein rarer conditions have very few samples) resulting in bias towards diagnosing common diseases and away from rarer diseases.
arXiv:2607. 23565v1 Announce Type: cross Abstract: Safe quadrotor navigation in cluttered and dynamic environments depends not only on instantaneous geometric perception, but more critically on anticipating collision risks induced by relative motion.
arXiv:2607. 23389v1 Announce Type: cross Abstract: Conventional CAPTCHAs pose puzzles that modern AI systems increasingly solve, while behavioral and cryptographic-attestation defenses carry privacy or enrollment costs.
arXiv:2607. 24577v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents are increasingly deployed in safety-critical domains such as robotics, autonomous driving, and drone control, where unexpected behaviors may lead to severe real-world consequences.
arXiv:2607. 24608v1 Announce Type: new Abstract: This work investigates uncertainty decomposition and explainability in a deep learning-based framework for gyroscope bias correction.
arXiv:2607. 24435v1 Announce Type: cross Abstract: Large language models may easily assign personality labels from text, but model interpretability remains an open problem.
arXiv:2607. 24365v1 Announce Type: new Abstract: Autonomous fleets enable mobility platforms to coordinate idle vehicles directly, making fleet-wide rebalancing possible.
arXiv:2607. 24338v1 Announce Type: new Abstract: Unsupervised graph representation learning aims to derive meaningful node embeddings by capturing both structural and attribute information without relying on labeled data.
arXiv:2607. 24314v1 Announce Type: new Abstract: Predicting the absorption, distribution, metabolism, excretion and toxicity (ADMET) properties of small molecules remains a major challenge in drug discovery.
arXiv:2607. 24260v1 Announce Type: new Abstract: Modern LLM systems increasingly rely on knowledge-selection processes that produce high-value structured priors, such as ranked evidence, graph topology, multimodal alignment, and confidence signals.
arXiv:2607. 24168v1 Announce Type: new Abstract: Road crashes remain among the gravest threats to public safety, and preventing them is a defining task of transportation systems worldwide.
arXiv:2607. 23624v1 Announce Type: cross Abstract: Third-party API routers have become a common layer that unifies access across increasingly diverse LLM providers.
arXiv:2607. 24553v1 Announce Type: cross Abstract: Standardized echocardiography conclusions provide meaningful supervision for learning ECG representations of echocardiography-derived cardiac findings.
arXiv:2607. 23018v1 Announce Type: cross Abstract: Nonstationary Gaussian process (GP) models are powerful tools for capturing input-dependent variability by adapting to observed data.