Knowledge catalogue
arXiv:2604.11120v1 Announce Type: new Abstract: Personality imbuing customizes LLM behavior, but safety evaluations almost always study prompt-based personas alone. We show this is incomplete: prompti
arXiv:2604.10286v1 Announce Type: new Abstract: Autonomous language-model agents increasingly rely on installable skills and tools to complete user tasks. Static skill auditing can expose capability s
arXiv:2609.29167v1 Announce Type: new Abstract: Banking assistants must use account-specific information to answer requests and, in many cases, take actions through tools. Evaluating only the final re
arXiv:2609.27463v1 Announce Type: new Abstract: Distributed model predictive control (DMPC) often constructs both predictions and collision constraints from neighbor trajectories, so packet loss can r
arXiv:2411.01289v2 Announce Type: replace Abstract: Complex events originate from other primitive events combined according to defined patterns and rules. Instead of using specialists' manual work to
arXiv:2609.09735v1 Announce Type: cross Abstract: Healthcare systems, mental health, and public well-being are increasingly affected by cyberbullying and harmful online interactions. This paper presen
arXiv:2609.04921v1 Announce Type: cross Abstract: Diffusion probabilistic models can capture the multi-modal, interaction-rich distribution of joint future trajectories in driving scenes. We show that
arXiv:2608.28714v1 Announce Type: cross Abstract: Objective: Deep learning accelerates brain MRI four- to tenfold, but models can erase lesions or synthesize false tissue - failures pixel-averaged met
arXiv:2608.30141v1 Announce Type: cross Abstract: Preference optimization is widely used to align large language models with human preferences, but preference-data composition may also influence priva
arXiv:2608.17659v1 Announce Type: cross Abstract: LLM-powered GUI agents that autonomously operate smartphones are rapidly transitioning from research prototypes to early real-world deployment. Howeve
arXiv:2608.09476v1 Announce Type: cross Abstract: Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API. We define behavio
arXiv:2607.28503v3 Announce Type: replace Abstract: In this paper we present an active, constantly updated AI benchmark which measures the integrity of frontier language models against being co-opted
arXiv:2608.06984v1 Announce Type: cross Abstract: Modern agent harnesses persist state across tasks and sessions through persistent carriers like memory, skills, tools, and shared artifacts. However,
arXiv:2608.03745v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning offers a promising window into model monitoring. However, monitoring relies on faithfulness, i.e., the model output str
arXiv:2608.02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form. We ask whether that reading is f
arXiv:2409.07314v4 Announce Type: replace Abstract: While Large Language Models (LLMs) achieve superhuman performance on standardized medical licensing exams, these static benchmarks have become satur
arXiv:2607.26802v1 Announce Type: new Abstract: This paper presents a radial basis function network (RBFN)-informed motion planning framework for safe and efficient urban autonomous driving. The propo
arXiv:2607.25518v1 Announce Type: new Abstract: Computational AMP discovery is often evaluated through AMP/non-AMP recognition, yet follow-up decisions depend on assay-derived evidence such as target-
arXiv:2607.20121v1 Announce Type: new Abstract: LLM-based agents leverage third-party skills to extend their capabilities in open-world scenarios. However, third-party skills can introduce extra secur
arXiv:2604.02694v2 Announce Type: replace-cross Abstract: The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safet
arXiv:2607.07695v1 Announce Type: new Abstract: We introduce institutional red-teaming, an evaluation methodology for testing deployment rules in multi-agent AI: hold the agents, objectives, and task
arXiv:2607.07229v1 Announce Type: new Abstract: Prior work has shown that chain-of-thought (CoT) reasoning is often unfaithful: a model's stated reasoning does not reliably reflect the process that pr
arXiv:2604.16870v2 Announce Type: replace-cross Abstract: AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP). These tool calls are the age
arXiv:2606.05233v1 Announce Type: cross Abstract: Recent computer-using-agent (CUA) red-teaming papers report prompt-injection attack success rates (ASR) of 42-98%, but these headline numbers cluster
arXiv:2606.04867v1 Announce Type: new Abstract: As AI companion platforms such as Replika and Character.AI rapidly grow, concerns about unsafe human-AI interactions have intensified. This study introd
OpenAI Group PBC’s newly released proposal for how advanced artificial intelligence should be regulated differs slightly from the Trump administration’s executive order, also released this week. Relea
arXiv:2606.00027v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed across healthcare, yet existing benchmarks fail to capture model behavior under adversarial or
arXiv:2606.01481v1 Announce Type: new Abstract: With the rapid advancements in text-to-image diffusion models, generative video models (T2V models) like Sora can now produce short synthetic videos fro
arXiv:2606.02443v1 Announce Type: cross Abstract: Between the first visible sign of danger and the moment an accident occurs, there is often a window where intervention remains possible. Video-capable
arXiv:2606.00801v1 Announce Type: cross Abstract: Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode colla
arXiv:2605.19869v1 Announce Type: cross Abstract: Construction remains the deadliest industry sector in the United States, with 1,055 fatal worker injuries recorded in 2023, and the majority preventab
arXiv:2512.06655v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract activation directions for inference-time steering, but their standard sparsity obj
arXiv:2605.13851v1 Announce Type: new Abstract: Multi-agent orchestration -- in which a hidden coordinator manages specialized worker agents -- is becoming the default architecture for enterprise AI d
arXiv:2605.14454v1 Announce Type: cross Abstract: As AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line
arXiv:2605.14604v1 Announce Type: new Abstract: This position paper argues that effective tutoring requires corrective friction: surfacing misconceptions and challenging them supportively to drive con
arXiv:2605.13709v1 Announce Type: cross Abstract: Large Language Models (LLMs) are widely applied in educational practices, such as for generating children's stories. However, the generated stories ar
This podcast episode from Last Week in AI discusses recent developments in large language models, including updates on GPT 5.5 and DeepSeek V4, while also covering concerns about potential sabotage or
arXiv:2510.22609v2 Announce Type: replace Abstract: Accurate symptom-to-disease classification and clinically grounded treatment recommendations remain challenging, particularly in heterogeneous patie
arXiv:2603.28013v3 Announce Type: replace-cross Abstract: Multi-agent LLM systems are entering production -- processing documents, managing workflows, acting on behalf of users -- yet their resilience
arXiv:2604.05172v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evalu
arXiv:2610.15422v1 Announce Type: new Abstract: Haptic shared control in surgical robotics combines human-side and robot-side forces at a shared end effector while preserving operator involvement. How
OpenAI released 719 mathematics manuscripts on October 6, 2026 that were generated by an internal frontier model (not publicly available), covering 372 topic families—including a solution to the Navie
arXiv:2610.06748v1 Announce Type: cross Abstract: In decentralized consumer-to-consumer (C2C) marketplaces, people list goods, negotiate with strangers, and rate one another, so trust rests on reputat
arXiv:2609.19767v1 Announce Type: new Abstract: True machine intelligence requires transcending passive pixel registration to master top-down functional reasoning over absent information via visual ne
arXiv:2609.16724v1 Announce Type: new Abstract: Safe local planning requires forecasting surrounding-agent motion and evaluating candidate-specific risks, since identical agent motion can pose differe
arXiv:2609.13236v1 Announce Type: new Abstract: Humanoid robots are becoming an important part of embodied artificial intelligence, driven by advances in reinforcement learning for locomotion, world m
arXiv:2608.06110v1 Announce Type: new Abstract: This paper presents ECHO (Enhanced Care & Health Observer), a locally-deployable conversational health assistant for long-term chronic care management.
arXiv:2608.05018v1 Announce Type: new Abstract: Short-term load forecasting (STLF) play a vital role in the electric power industry. It serves infrastructure that European and German law designate as
arXiv:2608.00600v1 Announce Type: new Abstract: Standard multifingered grasp execution architectures plan a collision-free trajectory to a selected grasp pose and track it with a feedback law. Executi
Cybersecurity chiefs at the White House have reportedly finalized the outline of a forthcoming framework that will enable artificial intelligence companies to voluntarily submit their latest frontier
arXiv:2607.24392v1 Announce Type: cross Abstract: Jailbreak defenses are essential for protecting large language models (LLMs), but they can also introduce secondary costs that weaken model utility. W
Anthropic PBC today rolled out a large language model called Claude Opus 5 to its chatbot service and developer platform. The company says the LLM approaches the output quality of its top-end Mythos 5
Anthropic PBC today debuted Claude Sonnet 5, a midrange large language model that outperforms its predecessor in several areas. The LLM will be the default option in the consumer tiers of the company’
arXiv:2606.22528v2 Announce Type: replace Abstract: Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget. We show t
arXiv:2606.26686v1 Announce Type: new Abstract: In order to screen a prompt or a response, the recent guardrail methods generate a chain-of-thought (CoT) before they issue a verdict. This design follo
arXiv:2606.07016v1 Announce Type: cross Abstract: Vulnerable road users (VRUs) account for approximately half of urban traffic deaths globally, with intersections concentrating a disproportionate shar
arXiv:2606.02630v1 Announce Type: cross Abstract: Patient-facing medical chatbots are commonly evaluated on single-turn prompts, yet real users push back after refusals, add urgency, and invoke author
arXiv:2605.26159v1 Announce Type: cross Abstract: Large language models are increasingly used as orchestrators of external tools via the Model Context Protocol (MCP), but MCP is built for software ser
arXiv:2507.06513v3 Announce Type: replace Abstract: Advances in vision-based sensors and computer vision algorithms have significantly improved the analysis and understanding of traffic scenarios. To
arXiv:2605.08878v1 Announce Type: cross Abstract: Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representa