Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.03625v1 Announce Type: cross Abstract: Relational databases are among the most widely deployed forms of structured knowledge, and natural language access to them requires grounding languag...
arXiv:2610.02664v1 Announce Type: new Abstract: Long-horizon agents are now playing an increasingly significant role in assisting humans with complex problem-solving. However, it is exactly their ext...
arXiv:2602.16543v2 Announce Type: replace Abstract: Safe reinforcement learning (Safe RL) learns robotic controllers that optimize task rewards under safety constraints, yet observation perturbations...
arXiv:2602.01124v4 Announce Type: replace Abstract: Dynamic graph representation learning requires capturing both structural relations and temporal evolution, yet existing approaches face a core trad...
arXiv:2610.02516v1 Announce Type: cross Abstract: Zero-shot classifiers are useful for routing user requests to specialized LLM tasks, but scoring every request against a large candidate set is expen...
arXiv:2610.02520v1 Announce Type: cross Abstract: We study online learning in episodic tabular constrained Markov decision processes with step-wise safety constraints. In such a setting, the constrai...
arXiv:2610.02552v1 Announce Type: cross Abstract: Machine learning-based intrusion detection systems (IDS) are critical for securing Industrial Internet of Things (IIoT) environments. Most adversaria...
arXiv:2602.18674v2 Announce Type: replace Abstract: We present a theoretical study of the robustness of parameterized neural networks to random input perturbations. Specifically, we analyze local rob...
arXiv:2606.27752v2 Announce Type: replace Abstract: Single-cell perturbation models can reduce costly wet-lab screening by predicting how cells respond transcriptionally to interventions. Recent adva...
arXiv:2610.02873v1 Announce Type: cross Abstract: The evolution of linguistic style in conversations is an underexplored issue in NLP. Most style-control datasets focus on sentences or assume a stati...
arXiv:2610.02928v1 Announce Type: cross Abstract: Invariant suites and runtime monitors increasingly gate agent deployment decisions, and the evidence offered for any particular suite is almost alway...
arXiv:2610.03036v1 Announce Type: cross Abstract: We present WebFovea, a vision-based web agent that placed 2nd in the WebRetriever Challenge 2026 with a final score of 57.0 out of 100. The challenge...
arXiv:2610.02574v1 Announce Type: new Abstract: High-fidelity solubility prediction is fundamental to pharmaceutical development and environmental partitioning, where accurate modeling must couple mo...
arXiv:2610.03033v1 Announce Type: new Abstract: Large language model (LLM)-based agents increasingly operate in multi-agent systems (MAS) characterised by strategic interaction. However, little is kn...
arXiv:2605.27586v2 Announce Type: replace-cross Abstract: Ensuring aligned agent behaviors in distributed open multi-agent systems remains challenging, especially as populations grow and unaligned ag...
arXiv:2406.00092v2 Announce Type: replace Abstract: Randomness is central to human cognition and to many applications in which large language models are deployed, yet probabilistic token generation d...
arXiv:2511.03756v2 Announce Type: replace-cross Abstract: We present a bifidelity Karhunen--Lo\`{e}ve expansion (KLE) surrogate model for field-valued quantities of interest (QoIs) under uncertain in...
arXiv:2605.00269v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detectors prioritize inputs for closer inspection. Yet features that distinguish input groups need not yield a usef...
arXiv:2610.03698v1 Announce Type: new Abstract: Self-supervised Vision Transformers (ViTs), such as DINOv2, learn rich visual representations, but the functions of their internal tokens remain poorly...
arXiv:2603.20103v4 Announce Type: replace-cross Abstract: Forward-backward (FB) representations provide a powerful framework for learning the successor representation (SR) in continuous spaces by enf...