cập nhật 1 giờ trước

⏱ 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.

28
Manga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard Planning
📄 Paper HF Daily Papers 29 ngày trước

Adapting existing manga into coherent animation that stays faithful to the source is a valuable yet challenging task. Existing methods either access the manga mainly through text, losing its characters and art style, or feed manga pages directly into video generation models, whic…

🅲 hạng C
28
Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V
📄 Paper HF Daily Papers 28 ngày trước

Code-based video generation offers fine-grained control, targeted editing, and component reuse compared with direct video generation. This approach requires multimodal large language models (MLLMs) to translate visual and temporal requirements into executable programs that produc…

🅲 hạng C
28
Evolving Infra: Agent-Adaptive LLM Serving at Scale
📄 Paper HF Daily Papers 8 ngày trước

Agentic workloads are a major source of LLM inference demand. Existing prefill--decode (PD) disaggregated serving systems offer limited flexibility for runtime adaptation of compute allocation and KV cache management, and rely on coarse signals that only partly capture the divers…

🅲 hạng C
28
DiffResearch: Accelerating Deep Research with Diffusion Language Models
📄 Paper arXiv cs.AI 25 ngày trước cũng có trên: HF Daily Papers

arXiv:2610.28909v1 Announce Type: new Abstract: Deep research systems iteratively plan, gather evidence, synthesize, and revise, making end-to-end latency a key bottleneck for interactive use. Almost all production systems are built on autoregressive (AR) language models and inh…

🅲 hạng C
28
AgentVQA: A Unified Benchmark for Agentic Visual Understanding
📄 Paper HF Daily Papers 26 ngày trước

Vision-language models (VLMs) can perform a broad range of tasks across diverse settings, yet their performance in agentic contexts remains poorly understood. Although online evaluations in simulators and real-world environments are essential for measuring interactive agent perfo…

🅲 hạng C
28
What It Is, Not What It Says: Securing Agentic Browsing Interactions with Web Semantics
📄 Paper arXiv cs.CR 28 ngày trước cũng có trên: HF Daily Papers

arXiv:2610.22697v1 Announce Type: new Abstract: AI agents increasingly browse the web on users' behalf, yet they consume webpages as screenshots or text, exposing their LLMs to unvetted third-party content. Browsers enforce semantics under which what an element can do depends on…

🅲 hạng C
28
ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination
📄 Paper HF Daily Papers 27 ngày trước

Forming an accurate theory-of-mind (ToM) is key to successful multi-agent collaboration and requires reasoning under uncertainty to capture multiple possible partner states. This is hard to do in the text representation space native to large language model (LLM) agents, which mor…

🅲 hạng C
28
MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation
📄 Paper HF Daily Papers 28 ngày trước

In a hierarchical multi-agent system, a Leader assigns tasks and subagents carry them out. Jointly training the Leader and the subagents is difficult because a final answer gives only indirect feedback to the subagents. An LLM judge can score the performance of the subagents, but…

🅲 hạng C
28
EditAgent: Rethinking Agentic Image Editing
📄 Paper HF Daily Papers 19 ngày trước

Agentic image editors decompose complex requests into steps, but when a step fails, they mostly retry with the same narrow set of tools and a judge that scores each output by eye directly. We argue that such agents are bounded by two spaces: the action space of what the agent can…

🅲 hạng C
28
Tail-risk-aware Agent Safety: Constraining Tail Risks Across Multi-step LLM Agent Workflows
📄 Paper arXiv cs.AI 6 ngày trước

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…

🅲 hạng C
28
The Devil Wears Markdown: Detecting Malicious Intent Hidden in AI Agent Skill Instructions through Hybrid Static, Dynamic, and Agentic Analysis
📄 Paper arXiv cs.CR 6 ngày trước

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…

🅲 hạng C
28
Tracing MCP Security Vulnerabilities: Constructing and Analyzing an MCP Security Vulnerability Dataset
📄 Paper arXiv cs.CR 6 ngày trước

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…

🅲 hạng C
28
Agentic Attribution of Cloud Resource Ownership
📄 Paper arXiv cs.CR 6 ngày trước

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…

🅲 hạng C
28
EnvLunch: The Environment as a Free Lunch for Learning to Interact
📄 Paper HF Daily Papers 24 ngày trước

For agentic data analysis, language-model agents often require a large number of annotated tasks to learn how to interact effectively with executable environments (i.e., databases). While high-quality annotated tasks require heavy manual effort, an executable environment already …

🅲 hạng C
28
Adversarial Speculative Reasoning Improves Long Horizon Agents
📄 Paper HF Daily Papers 14 ngày trước

Speculative decoding has been treated purely as a systems optimization that speeds up large language model decoding without changing the model behavior. Under this view, the growing effort to train better draft models has been focused solely on acceptance rate. We argue that this…

🅲 hạng C
28
Provable Authority: A Protocol for Verifiable Authority Resolution and Control Across Human, Organizational, and Agentic Transactions
📄 Paper arXiv cs.CR 28 ngày trước

arXiv:2610.22899v1 Announce Type: new Abstract: Payment systems authenticate users, devices, accounts, and cryptographic credentials, but a relying party, such as a counterparty, payment rail, marketplace, or autonomous agent runtime, generally cannot obtain compact, independent…

🅲 hạng C
28
ABF-Bench: A Verifiable Benchmark for Agentic Blockchain Forensics
📄 Paper arXiv cs.CR 28 ngày trước

arXiv:2610.23656v1 Announce Type: new Abstract: Blockchain forensics is adversarial and open-ended: money launderers split, swap, and bridge funds, cut their trail at mixers or custodial services, and change tactics from one incident to the next. Investigators must keep adapting…

🅲 hạng C
28
Doing Less with More: A First-Principles Exploration of the Suitability of Agentic Computing over Alternative Architectural Choices
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.23921v1 Announce Type: new Abstract: There is growing interest in automating business activities with Agentic Artificial Intelligence (AI) due to latter's seeming ease of use. Never has it been easier, or costlier, to do less with more. However, little is known about …

🅲 hạng C
28
Narratives Mislead: An Empirical Study of How LLMs Misjudge CVSS Severity in Bug Bounty Reports
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.24623v1 Announce Type: new Abstract: Bug bounty platforms receive vulnerability reports faster than vendors can triage them, and Large Language Models (LLMs) are increasingly considered for assigning the Common Vulnerability Scoring System (CVSS) severity that drives …

🅲 hạng C
28
Peer Pressure: Execution-Verified Co-Evolution of Attacker and Defender Populations for Code Security
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.24896v1 Announce Type: new Abstract: LLM code agents increasingly ship code with little oversight, yet defenders trained on static vulnerability datasets fall behind adapting adversaries. We co-train attacker and defender instead, and let execution decide every reward…

🅲 hạng C