Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2605.06524v3 Announce Type: replace Abstract: Reliable human-machine discrimination is becoming increasingly important as Large Language Models and autonomous agents are deployed in online sett...
arXiv:2605.09278v2 Announce Type: replace Abstract: Multi-agent debate (MAD) systems increasingly rely on shared memory to support long-horizon reasoning, but this convenience opens a critical vulner...
arXiv:2605.14542v2 Announce Type: replace Abstract: A skilled live-commerce host is not merely a narrator, but a sales agent who converts viewer curiosity into purchase intent through expert product...
arXiv:2605.17734v2 Announce Type: replace Abstract: Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-h...
arXiv:2609.32964v2 Announce Type: replace Abstract: Language models (LMs) often hallucinate by committing to confident answers rather than abstaining, even when they do not have enough information to...
arXiv:2609.34799v2 Announce Type: replace Abstract: Language-conditioned trajectory generation is here, but its evaluation has not kept pace. Existing pedestrian trajectory metrics compare trajectori...
arXiv:2609.34653v2 Announce Type: replace Abstract: On-device streaming omni-modal inference safeguards user privacy and eliminates prohibitive per-token API costs, but faces a critical bottleneck: t...
arXiv:2506.11261v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models have shown promising progress in robotic manipulation. However, directly mapping visual observations and...
arXiv:2509.20411v3 Announce Type: replace-cross Abstract: Machine learning-based cybersecurity systems are highly vulnerable to adversarial attacks, while Generative Adversarial Networks (GANs) act a...
arXiv:2510.22752v2 Announce Type: replace-cross Abstract: In-context learning is governed by both temporal and semantic relationships, shaping how Large Language Models (LLMs) retrieve contextual inf...
arXiv:2602.20144v2 Announce Type: replace-cross Abstract: We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP...
arXiv:2604.03114v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) may need to forget visual concepts after deployment because of privacy, copyright, licensing, safety, or policy...
arXiv:2605.01970v4 Announce Type: replace-cross Abstract: Memory systems enable otherwise stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. Th...
arXiv:2607.13038v2 Announce Type: replace-cross Abstract: Conversational AI can improve access to public health information, but public-facing healthcare applications require safeguards against inapp...
arXiv:2609.33923v2 Announce Type: replace-cross Abstract: A single random Gaussian probe gives an unbiased estimate of the squared Frobenius norm of a layer's quantization error. The estimator is wel...
arXiv:2609.34790v2 Announce Type: replace-cross Abstract: LLM agents operate in persistent collaborative environments involving multiple users, communities, memories, files, and tools. Community boun...
arXiv:2609.36030v1 Announce Type: new Abstract: The lack of rigorous safety and performance certificates remains a key bottleneck to the deployment of modern learning-based methods. Sample compressio...
arXiv:2609.36174v1 Announce Type: new Abstract: We consider fair resource allocation in sequential decision-making environments modeled as major-minor weakly coupled Markov decision processes (M2WCMD...
arXiv:2609.36633v1 Announce Type: new Abstract: This paper proposes a physics-guided gradient-ascent-based machine unlearning method that couples the forgetting signal with the physical residual of t...
arXiv:2609.36686v1 Announce Type: new Abstract: Identifying the root cause of an anomaly among hundreds of sensors is critical for preventing safety incidents and costly downtime in complex monitored...