cập nhật 11 phút trước

⏱ 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.

26
WAKMan: Workload Aware KVCache Manager
📄 Paper arXiv cs.AI 21 ngày trước

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. …

🅲 hạng C
26
Blindfold: Keeping the Audit Coin Secret from LLM Agents
📄 Paper arXiv cs.CR 21 ngày trước

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…

🅲 hạng C
26
Capability-Grounded Agentic Planning
📄 Paper arXiv cs.AI 16 ngày trước

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 …

🅲 hạng C
26
BABA-Bench: Evaluating Long-Horizon Patient-Advocacy Agents
📄 Paper arXiv cs.AI 16 ngày trước

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…

🅲 hạng C
26
CIRCE Divines LLM Task Complexity from Constraint Structure
📄 Paper arXiv cs.AI 16 ngày trước

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…

🅲 hạng C
26
Counterfactual Pairwise Augmentation Improves Small Pointwise LLM Judges
📄 Paper arXiv cs.AI 16 ngày trước

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…

🅲 hạng C
26
Characterizing LLM Agent Behaviors in Module Shadowing Environments
📄 Paper arXiv cs.CR 16 ngày trước

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…

🅲 hạng C
26
SecPO: Principled Adversarial Training for Prompt Injection Security
📄 Paper arXiv cs.CR 16 ngày trước

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 …

🅲 hạng C
26
Low-Margin Branch Points in Deterministic LLM Deliberatio
📄 Paper arXiv cs.AI 15 ngày trước

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,…

🅲 hạng C
26
Unsatz: Evaluating Scientific Discovery Without a Given Ansatz
📄 Paper arXiv cs.AI 14 ngày trước

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…

🅲 hạng C
26
A Guideline-Grounded Multi-Agent Framework for Personalized Exercise Prescription from Clinical and Wearable Data
📄 Paper arXiv cs.AI 14 ngày trước

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…

🅲 hạng C
26
Can Benign Skills Induce Misaligned Behavior in LLM Agents?
📄 Paper arXiv cs.CR 14 ngày trước

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…

🅲 hạng C
26
Anduin: A sybil-resistant agentic marketplace reputation system
📄 Paper arXiv cs.AI 13 ngày trước

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 …

🅲 hạng C
26
Don't Prompt Your Agents. Equip Them: Skillware as a Modular Standard for Sovereign, Auditable, and Deterministic Capability Execution for Logical Systems
📄 Paper arXiv cs.AI 12 ngày trước

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…

🅲 hạng C
26
The Promise of Strategic Agentic Scambaiting
📄 Paper arXiv cs.CR 12 ngày trước

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…

🅲 hạng C