arXiv:2611.17797v1 Announce Type: new Abstract: Multimodal agentic coding requires robust visual reasoning to analyze observations and evaluate generated artifacts. Current frameworks largely rely on a Thinking-with-Images paradigm, where agents depend on their intrinsic vision …
⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5336, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.17639v1 Announce Type: new Abstract: Before an LLM agent cancels a reservation or deletes a folder for a user, what stops it from acting on a false assumption: what its tools show, or what the user says? In this work, we study this gap with presupposition theory from …
arXiv:2611.17856v1 Announce Type: new Abstract: Tools for interpreting the internal representations of Large Language Models (LLMs) increasingly rely on LLMs themselves to both generate and evaluate explanations, creating a self-referential automated interpretation process with …
Frontier LLM agents that query databases with tools are among the most accurate text-to-SQL systems, but per-query calls to a hosted model are slow, costly, and expose sensitive organizational queries to external APIs. For example, a Claude Opus 5.5 agent serving 10,000 queries a…
arXiv:2611.12953v1 Announce Type: new Abstract: Enterprises increasingly use large language model agents to execute standard operating procedures (SOPs): long, branching, tool-intensive workflows. Yet there is little controlled evidence for choosing among competing agentic archi…
arXiv:2611.13020v1 Announce Type: new Abstract: Electronic design automation (EDA) workflows remain highly fragmented, requiring engineers to coordinate heterogeneous representations, specialised software tools, and iterative verification across multiple design stages. Although …
arXiv:2611.13196v1 Announce Type: new Abstract: LLM-based agents can reason, use tools and collaborate. However, coordinating increasingly complex agentic applications becomes difficult to understand, monitor and improve. Decisions distributed across prompts, tool calls and appl…
arXiv:2611.10411v1 Announce Type: new Abstract: LLM-based agents extend LLMs with tool calls, memory, planning, and retrieval to act in external environments, but they are vulnerable to attacks at different workflow steps. Existing defenses, including prompt engineering and post…
arXiv:2611.10453v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) rollouts interleave model reasoning with tool calls in persistent workspaces. Scaling these rollouts incurs substantial memory costs for concurrent environments, while slow tool calls delay entir…
arXiv:2611.10612v1 Announce Type: new Abstract: As enterprise systems grow in scale and complexity, manual log analysis and conventional SIEM tools struggle to keep pace with the volume and diversity of incidents. To address this challenge, this paper proposed a multi-agent AI f…
arXiv:2611.10830v1 Announce Type: new Abstract: Agentic AI ecosystems increasingly rely on reusable agent skills that combine executable code, natural-language instructions, configuration artifacts, and external tool integrations. These hybrid artifacts create software supply-ch…
arXiv:2611.10843v1 Announce Type: new Abstract: Agentic AI systems extend large language models with tools, memory, retrieval, browser or computer-use interfaces, code execution, external services, and multi-agent coordination. Although these capabilities enable agents to act be…
arXiv:2611.11104v1 Announce Type: new Abstract: As a core protocol for integrating large language models (LLMs) with external data sources and tools, the Model Context Protocol (MCP) has quickly become a key interface in emerging AI agent systems. As the MCP ecosystem expands, r…
arXiv:2611.11266v1 Announce Type: new Abstract: As enterprises delegate consequential work to multi-agent LLM systems, benign-looking requests can escalate into unsafe actions as they propagate across sessions through poisoned shared state, long-context documents, and trusted pe…
arXiv:2611.11340v1 Announce Type: new Abstract: Security tools raise findings across cloud environments, and AI agents now investigate and prioritize them. A finding is still resolved by people: it has to reach the people responsible for fixing it and accountable for the resourc…
arXiv:2611.17632v1 Announce Type: new Abstract: Generating an evaluation suite from an agent's specification is diversity-driven search: a generator fills a descriptor space (requirements $\times$ personas $\times$ scenario kinds), and the suite it emits is an archive, then scor…
arXiv:2611.15006v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly interact with tools and environments, yet plausible model decisions do not always translate into successful execution due to tool-call mismatches, interrupted workflows, and unsupporte…
arXiv:2611.15223v1 Announce Type: new Abstract: Large-language model (LLM) agents execute actions on external systems through tool calls, and enterprises deploy runtime controls, such as agent gateways, to check this behavior in real time. However, a control can only evaluate th…
arXiv:2611.16158v1 Announce Type: new Abstract: LLM agents apply approval settings, such as whether to ask before a consequential tool call, through instructions in their system prompt, and operators keep these settings confidential by restricting access to prompts and responses…
Autonomous agents modify prompts, memories, tools, workflows, and policies using interaction histories. Yet a plausible modification is not necessarily suitable for persistent adoption: candidate selection is adaptive, evaluators may be imperfect, and local gains can hide degrada…
arXiv:2611.13144v1 Announce Type: new Abstract: Effective teaching requires reasoning about the learner as well as the task, a capacity that Theory of Mind describes as inferring another agent's latent state from its behavior. We ask whether a stronger LLM teaches a fixed studen…
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…
arXiv:2611.11305v1 Announce Type: new Abstract: LLM agents that call tools are exposed to indirect prompt injection: instructions hidden in tool outputs can steer an agent into calls the user never asked for. We present a runtime audit that derives an executable intent graph fro…
The release of GPT-6 Astra marks the emergence of a new paradigm in robotics: agentic robotics. Within weeks, frontier models with agentic harnesses matched or exceeded task-specific policies on many embodied benchmarks. Instead of training a dedicated policy for each family of t…
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:2611.14654v1 Announce Type: new Abstract: Tool-using language-model agents accumulate histories of their own mistakes, and a system that compacts, repairs or hands off such a history decides what it says about those mistakes while their effects stay in the world. Prior wor…
arXiv:2611.15276v1 Announce Type: new Abstract: Agent self-improvement requires feedback about task success, yet external feedback may be unavailable at test time. Agents must then infer success from observable evidence, and incomplete verification can misguide subsequent update…
arXiv:2611.14864v1 Announce Type: new Abstract: An AI agent's decision not to act can itself become an attack surface. We study warning-induced over-abstention, an availability attack in which adversaries place fabricated risk warnings in low-trust content to prevent legitimate …
arXiv:2611.16122v1 Announce Type: new Abstract: AI agents increasingly access enterprise data, invoke powerful tools, and act with limited human oversight. Existing security defenses primarily detect prompt injection, harmful outputs, or suspicious behavior, but do not determine…
Standard coding-agent benchmarks primarily evaluate binary task success, treating execution as a black box and obscuring the behaviors that produce those outcomes. We analyze a large corpus of 143,209 execution trajectories from 125 agent configurations spanning 117 unique models…
arXiv:2611.12934v1 Announce Type: new Abstract: While multimodal agents now carry out complex data analysis with tools, their ability to turn decades of satellite imagery into reliable land-change analysis, crucial for Earth observation science, remains unmeasured. Existing benc…
arXiv:2611.13006v1 Announce Type: new Abstract: Medical vision-language models (VLMs) often report a finding because the question names it; standard benchmarks miss this. From public segmentation datasets we build counterfactual views without manual annotation: the lesion erased…
arXiv:2611.17495v1 Announce Type: new Abstract: Chain-of-thought (CoT) is currently a valuable tool for overseeing AI models, but some architectural shifts could significantly reduce CoT monitorability. We operationalize a measure that serves as a proxy for the amount of unverba…
arXiv:2611.17747v1 Announce Type: new Abstract: Photo-Response Non-Uniformity (PRNU) is the de facto standard trace for sensor-level source-camera attribution, and a high Peak-to-Correlation-Energy (PCE) between a questioned image and a camera reference fingerprint is routinely …
arXiv:2506.15253v2 Announce Type: replace Abstract: As large language model (LLM) agents are increasingly deployed in long-horizon unattended scenarios, security evaluation of them before deployment becomes increasingly essential and challenging. Existing evaluation methods main…
arXiv:2611.15316v1 Announce Type: new Abstract: Building and evaluating security tools for IoT firmware requires targets whose weaknesses are known in ad- vance and can be reproduced in a running device. Two problems remain: (1) firmware collected from real-world products provid…
arXiv:2611.15472v1 Announce Type: new Abstract: Signed PDF documents have legally binding value under frameworks such as the EU's eIDAS regulation. In this work, we present Genuine PDF Forgeries, a novel attack class that focuses on human factors in signature validation. Our att…
arXiv:2611.14362v1 Announce Type: new Abstract: As electric vehicle (EV) adoption accelerates globally, securing electric vehicle charging station (EVCS) software becomes increasingly critical. The Open Charge Point Protocol (OCPP), widely adopted for EVCS management, places sig…
arXiv:2611.10261v1 Announce Type: new Abstract: The phrase recursive self-improvement (RSI) refers to the idea of an AI system designing and creating another, better AI system, which in turn designs and creates an even better one, and so on. While the idea has a long history, it…
arXiv:2611.10425v1 Announce Type: new Abstract: Local-first security tools let organizations analyze code without sending it to third-party services, but the small language models they can run locally are weaker than hosted ones and are hard to improve without breaching the priv…