arXiv:2610.36355v1 Announce Type: new Abstract: Prefix caching enables a Large Language Model (LLM) servers to reuse the Key-Value (KV) states and accelerate prefill computation stage for requests that share a prefix with earlier prompts, thus reducing latency and serving cost. …
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5464, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2610.36435v1 Announce Type: new Abstract: LLM agents increasingly interact with other agents on behalf of users, yet how users in the loop affect their agents' behavior--for better or worse--remains poorly understood. We study this question through the lens of negotiation,…
arXiv:2610.36471v1 Announce Type: new Abstract: LLM agents interact with Web services to perform tasks on users' behalf. Errors during these interactions can disrupt execution and prevent task completion, motivating external intervention. However, agents may self-recover through…
arXiv:2610.36711v1 Announce Type: new Abstract: Reliable evaluation is a critical bottleneck in privacy red-teaming of large language models (LLMs): determining whether a jailbreak response actually reveals personal information can be difficult when disclosures are indirect, con…
arXiv:2610.37055v1 Announce Type: new Abstract: Audit-based certification bounds the violation rate of an LLM agent by auditing a random fraction $\varepsilon$ of actions and reweighting the audited labels; its validity is meant to rest only on the defender's audit coin. We show…
arXiv:2610.37415v1 Announce Type: new Abstract: Prior work framed the envelope layer as the channel through which malicious content enters an agent, and established it as a defense surface independent of the LLM layer and the agent layer; however, that work only tested the envel…
As frontier language models grow increasingly capable and autonomous, independent third-party evaluations are critical for characterizing their systemic safety risks. While closed-source releases are routinely accompanied by comprehensive system cards, open-weight models receive …
arXiv:2610.41040v1 Announce Type: new Abstract: LLM agents serve natural-language requests through tools, data sources, and other agents, and even simple requests often need several interdependent calls. Typically, the LLM picks these calls by trial and error, with no guarantee …
arXiv:2610.41076v1 Announce Type: new Abstract: An LLM agent that helps a patient get care must do two things. It must reach the correct outcome, and it must follow the necessary procedure. For example, the agent must get the patient's permission before it shares the patient's r…
arXiv:2610.41089v1 Announce Type: new Abstract: Estimating whether a problem is too complex for a large language model (LLM) before the model attempts it can guide model routing, how to allocate test-time compute, and suggest the need for new tools to aid the agent. While existi…
arXiv:2610.41124v1 Announce Type: new Abstract: Agentic LLM assistants must repeatedly decide whether to answer from memory or to call a tool such as web search. Unnecessary searches cost latency and money; missing ones yield confident but unsupported answers. Prior work mostly …
arXiv:2610.41149v1 Announce Type: new Abstract: Agentic systems increasingly gate individual steps with a pointwise judge that scores a response against a criterion. Small language models are attractive for this role because they can be served and specialized efficiently. Such a…
arXiv:2610.40716v1 Announce Type: new Abstract: LLM agents operating in untrusted workspaces face the risk of untrusted code execution during routine tasks, yet final reports and workspace states alone cannot reliably establish whether execution occurred. We introduce an evaluat…
arXiv:2610.41056v1 Announce Type: new Abstract: Since large language model (LLM) agents rely on long-term memory, what they store now shapes what they do later. A memory manager decides how each input changes this memory and which records the agent acts on. It can fail in two wa…
arXiv:2610.41401v1 Announce Type: new Abstract: Large language model agents interact with online services through tool calls that may access private data or perform sensitive actions. Specialized providers can supply and maintain pre-execution safety auditing capabilities for ag…
arXiv:2610.41998v1 Announce Type: new Abstract: Recognized as a top threat to AI agents, prompt injection allows instructions from untrusted data (email, documents, websites) to manipulate the agent's operation. The existing best-defended LLM, Meta-SecAlign, is trained with the …
arXiv:2611.00247v1 Announce Type: new Abstract: Dense labels of the aorta in CT are slow to draw, and the public aortic CT datasets that could stand in for them each label different structures under their own conventions. Large language model (LLM) agents can now write code and …
arXiv:2611.00546v1 Announce Type: new Abstract: Deterministic multi-agent LLM deliberation can exactly re- play a fixed transcript, yet exact replay alone does not test local resistance to controlled internal interventions. Because each response becomes context for later agents,…
arXiv:2611.00725v1 Announce Type: new Abstract: Coding agents increasingly operate with web access and high privileges, creating a new attack surface where web fraud can directly target autonomous agents. Existing studies mainly focus on malicious links, prompt injection, and in…
arXiv:2611.03713v1 Announce Type: new Abstract: Before a scientist fits any parameter, they must decide what the model contains: which quantities exist, which are hidden, how they interact, and how they are measured. Physicists call such a trial form an ansatz. Benchmarks for au…
arXiv:2611.03980v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used as synthetic participants in opinion-dynamics experiments, often assuming that an agent's behaviour is fully determined by its prompt. We test this assumption with a framework…
arXiv:2611.03983v1 Announce Type: new Abstract: Translating population-level exercise guidance into individualized prescriptions requires integrating clinical and wearable data, including diagnoses, medications, functional limitations, and baseline activity, with condition-speci…
arXiv:2611.04003v1 Announce Type: new Abstract: LLM agents struggle to automate complex enterprise procedures because static, pre-built harness cannot capture proprietary policies, undocumented behaviors, or state-dependent recovery paths that surface only during execution. Proc…
arXiv:2611.04299v1 Announce Type: new Abstract: LLM agents increasingly rely on reusable skills to plan tasks, invoke tools, recover from errors, and complete workflows without modifying model parameters. Although these skills are typically developed to enhance benign tasks, the…
arXiv:2611.04393v1 Announce Type: new Abstract: LLM agents increasingly act on information retrieved from public sources they treat as credible, which turns a manipulated recommendation into a transaction, a dependency, or a decision with physical consequences. The security lite…
arXiv:2611.04701v1 Announce Type: cross Abstract: A zero-knowledge virtual machine (zkVM) lets an untrusted prover convince a verifier that a program, typically Rust compiled to RISC-V, ran correctly. The proof covers the compiled binary, so a miscompilation can make a correct z…
Omni models answer questions about videos by jointly processing sampled frames and audio in one turn, with progress driven largely by scaling model size and omni training data. We ask whether a model needs to hear the audio directly at all, and present SleuthVLM, an agent harness…
arXiv:2611.05392v1 Announce Type: new Abstract: Agentic artificial intelligence (AI) systems powered by large language models (LLMs) execute as autonomous multi-step pipelines that dynamically invoke tools, integrate observations into memory, and iterate until a task is resolved…
arXiv:2611.05586v1 Announce Type: new Abstract: As autonomous AI agents enter permissionless onchain markets, selecting new service providers remains a core challenge. Existing reputation systems depend on scarce resources like human curation, identity credentials, or voluntary …
arXiv:2611.05759v1 Announce Type: new Abstract: Before an AI agent takes on a paid job, someone has to judge whether it is likely to succeed. We test whether frontier language models can make this call before any attempt. We propose PAYWORTHY which contains 1{,}494 real freelanc…
arXiv:2611.05791v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external memory stores to retain information across conversations, typically via dense vector embeddings searched with approximate nearest-neighbor methods. The fruit fly's olf…
arXiv:2611.05828v1 Announce Type: new Abstract: Intelligent production requires systems to make decisions and organize work according to production goals and operating conditions. It also requires continuous adjustment through feedback. This paper analyzes intelligence in human …
arXiv:2611.06294v1 Announce Type: new Abstract: Large language model (LLM) coding assistants and agents construct a repository context before generating code. For security-sensitive code, this context decides whether the model sees the project's safeguards (e.g., authorization c…
arXiv:2502.04953v2 Announce Type: replace Abstract: Static analysis techniques are often insufficient to determine whether a reported security vulnerability is exploitable and actually poses a real security risk to a software application. Dynamic analysis addresses this limitati…
arXiv:2611.06995v1 Announce Type: new Abstract: Artificial intelligence (AI) systems have ushered in a new age of proof abundance, but helping humans understand these proofs requires new attention to the differences in how AI agents and humans pursue a proof-making task. We pres…
arXiv:2611.07652v1 Announce Type: new Abstract: Current autonomous logical systems rely on a fragile assumption: that language models should dynamically write code, guess API payloads, and memorize operational constraints through prompt engineering. In practice, this burns massi…
arXiv:2611.07825v1 Announce Type: new Abstract: Goal interpretation is to translate a natural language instruction into a formal symbolic goal that a planner can execute. It is critical for embodied agents because any error here propagates to every downstream planning and action…
arXiv:2611.07483v1 Announce Type: new Abstract: Enterprise AI agents increasingly split a user's request across subagents and merge their results, and each handoff can summarize away, alter or ignore a requirement. We report a preregistered study with synthetic, exactly scorable…
arXiv:2611.08170v1 Announce Type: new Abstract: Scammers have increasingly adopted AI-driven capabilities, evolving from automated message generation to fully agentic conversational systems that scale operations and maximize the exploitation of fraudulent resources before detect…
arXiv:2609.22818v3 Announce Type: replace Abstract: Memory-poisoning defenses for LLM agents are usually judged by how well they stop attacks, yet almost all the traffic an agent sees is benign. We measure what these defenses cost when no attack is present. Our harness holds the…