arXiv:2611.12941v1 Announce Type: new Abstract: The rapid proliferation of autonomously acting AI agents makes the governance of agentic systems urgent. We propose the competence circuit, summarized as IKC + KC + C, that decomposes an agent's real-world impact into three pathway…
⏱ Độ trễ thật của tab này: trung bình 7.1 giờ sau khi CVE được công bố (n = 5332, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.10026v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly perform complex tasks using high-privilege tools, making indirect prompt injection (IPI) a critical security risk. However, IPI benchmarks lag behind their rapidly evolving utility cou…
AI agents deployed on the open web are becoming more capable of performing actions that may breach contractual provisions and violate computer security laws. In this paper, we introduce ScrapeBench, the first agentic benchmark for empirically evaluating the legal compliance of AI…
arXiv:2508.18370v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated exceptional capabilities when trained within executable runtime environments, notably excelling at software engineering tasks through verified feedback loops. Yet, scalable a…
Large language models (LLMs) are increasingly used by reviewers to highlight weaknesses during the reviewing process, and their outputs often shape the reviews that humans submit. Prior work studies how LLM reviews align with human ones, yet we know little about which parts of a …
arXiv:2611.17814v1 Announce Type: new Abstract: With the rapid advancement of Large Language Models (LLMs), an increasing number of users are turning to LLM-powered agents for conversational shopping in e-commerce. However, the user needs continue to change as new product catego…
arXiv:2611.14681v1 Announce Type: new Abstract: Today's AI workloads are rapidly changing: new models are released more often, model architectures are increasingly diverse, and traffic distributions change frequently. The challenge we face at Together AI is continual optimizatio…
arXiv:2611.10089v1 Announce Type: new Abstract: Large Language Models (LLMs) remain vulnerable to jailbreak attacks and harmful-content prompts, particularly under adversarial distribution shifts where static alignment pipelines fail to generalize. Although introspective methods…
arXiv:2611.10390v1 Announce Type: new Abstract: When disasters strike, they not only damage infrastructure, buildings, and the economy, but also affect the mental health of affected populations. Research on the mental health effects of disasters has expanded rapidly and has beco…
arXiv:2611.10399v1 Announce Type: new Abstract: Big techs and researchers increasingly claim that their training datasets are too large to inspect for bias and ethical problems. However, in the race to build ever-large models, they have relied on automated web scraping and no hu…
arXiv:2611.15019v1 Announce Type: new Abstract: Encrypted tunnels are widely used to circumvent censorship, which has drawn censors' efforts to detect and block them. As the circumvention tunnels in widest use have largely converged on TLS, detection has shifted from the content…
arXiv:2611.13022v1 Announce Type: new Abstract: AI systems can produce reliable results without developing human understanding. However, human understanding remains valuable for shaping subsequent AI-supported work, forming preferences, governing collective choices and satisfyin…
arXiv:2611.13965v1 Announce Type: new Abstract: MiniApps are increasingly central to super-app ecosystems, yet architectural differences complicate the transfer of security analysis techniques across platforms. Existing WeChat analyzers rely on packaged applications and platform…
arXiv:2504.18598v3 Announce Type: replace Abstract: Mixture-of-Experts (MoE) architectures are rapidly becoming the standard for building scalable and efficient large language models (LLMs), thanks to their routing mechanism that activates only a subset of experts for each input…
arXiv:2611.10109v1 Announce Type: new Abstract: The rapid expansion of AI-driven data center construction has outpaced public engagement: an estimated $64 billion in U.S. data center projects were blocked or delayed by local opposition between May 2024 and March 2025, yet the co…
Interpretability demonstrations often show that intervening on a group of neurons changes a model's answer. A recent example removes an 18-neuron group in Qwen3-32B and the model answers "Simba" instead of "Scar" to a two-hop Lion King riddle. Such a demonstration establishes tha…