Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 02186v1 Announce Type: new Abstract: Software development is a complex task that demands cooperation among agents with diverse roles.
arXiv:2607. 02507v1 Announce Type: new Abstract: LLM agents will increasingly act in socially structured settings where role, audience, and relational context can shape what is advantageous or costly to say.
arXiv:2607. 02288v1 Announce Type: cross Abstract: While pessimism counteracts overestimation bias in offline reinforcement learning (RL), being overly conservative has been associated with hindering certain forms of generalization.
arXiv:2607. 02097v1 Announce Type: cross Abstract: Large kernel depthwise convolutions achieve strong performance but suffer from significant degradation as kernel size grows due to irregular memory access from gather-based computation; while Large Kernel Acceleration (LKA) helps on small feature maps, it becomes counterproductive on large feature maps, even slower than non-accelerated implementations.
arXiv:2607. 02431v1 Announce Type: cross Abstract: Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction beyond the states observed in demonstrations.
arXiv:2607. 02432v1 Announce Type: new Abstract: Scalable and reliable grading of command-line examinations remains a challenge in computing education, where rising enrolments make manual marking difficult and rule-based autograders cannot handle partial credit, equivalent solutions, or syntactic variation.
arXiv:2607. 01474v1 Announce Type: new Abstract: Class imbalance poses a critical challenge in federated learning (FL), where underrepresented classes suffer from poor predictive performance yet cannot be addressed by standard centralized techniques due to privacy and heterogeneity constraints.
arXiv:2607. 01311v1 Announce Type: new Abstract: Deep learning has outgrown any single mathematical explanation.
arXiv:2603. 06001v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models enable robots to perform manipulation tasks directly from natural language instructions and are increasingly viewed as a foundation for generalist robotic policies.
arXiv:2607. 02079v1 Announce Type: cross Abstract: We present HaloGuard 1.
arXiv:2607. 01449v1 Announce Type: new Abstract: We propose a novel hybrid neural architecture, the Geometry-aware R-Structured Kolmogorov-Arnold Network (GRS-KAN), which integrates V.
arXiv:2604. 19775v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments.
arXiv:2602. 07267v2 Announce Type: replace Abstract: Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty.
arXiv:2511. 17089v2 Announce Type: replace-cross Abstract: We present Spanning Tree Autoregressive (STAR) modeling, which can incorporate prior knowledge of images, such as center bias and locality, to maintain sampling performance while also providing sufficiently flexible sequence orders to accommodate image editing at inference time.
arXiv:2607. 01846v1 Announce Type: new Abstract: Domain agents often face noisy business data, uncertain post-training gains, offline/application mismatch, and adapter-release risk.
arXiv:2607. 01287v1 Announce Type: cross Abstract: Accompanying a group of humans is an essential aspect of developing human-like social cognition in robots.
arXiv:2607. 01282v1 Announce Type: cross Abstract: In light of strides in Arti cial Intelligence (AI) and its wide spread application, challenges persist in the interpretability of AI models, particularly within specialized domains like healthcare, such as electro cardiograph (ECG) recognition.
arXiv:2607. 02121v1 Announce Type: cross Abstract: As Large Language Models (LLMs) and agentic systems become integrated into real-world applications, ensuring their safety and security is critical.
arXiv:2607. 01250v1 Announce Type: cross Abstract: Sociotechnical alignment concerns the social desirability of AI behavior and is thus inherently normative, not merely technical.
arXiv:2604. 14228v2 Announce Type: replace-cross Abstract: Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user.