cập nhật 59 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5417, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

29
Cyber-Zero: Training Cybersecurity Agents without Runtime
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2508.00910v3 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success in software engineering tasks when trained with executable runtime environments, particularly in resolving GitHub issues. However, such runtime environments are ofte…

🅲 hạng C
27
Agentic On-Policy Distillation Implicitly Reshapes LLMs' ReAct Patterns
📄 Paper arXiv cs.AI 22 giờ trước

arXiv:2611.19244v1 Announce Type: new Abstract: On-policy distillation (OPD) transfers specialized capabilities to language-model agents, but its cross-domain effects on interaction remain unclear. We investigate how OPD reshapes ReAct interaction patterns across mathematics, AL…

🅲 hạng C
27
HalluProbe: Exploiting VLM Hallucinations for Backdoor Detection
📄 Paper arXiv cs.CR 22 giờ trước

arXiv:2611.19868v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are vulnerable to backdoor attacks introduced through data poisoning, making effective backdoor detection a critical security challenge. In this paper, we uncover a novel connection between VLM halluci…

🅲 hạng C
27
CHERI under Fault Injection: An Emulation-Based Security Evaluation of Capability Hardware Enhanced RISC Instructions
📄 Paper arXiv cs.CR 22 giờ trước

arXiv:2611.19915v1 Announce Type: new Abstract: Memory-safety vulnerabilities continue to dominate real-world exploit chains despite decades of research into software mitigations. CHERI is a hardware architecture that enforces spatial and temporal memory safety by augmenting poi…

🅲 hạng C
26
When Expert Disagreement Hurts: Prestige and Selectivity in LLM Decision Revision
📄 Paper HF Daily Papers 6 ngày trước

When language models revise a decision after another agent disagrees, neither reversal counts nor final accuracy shows whether they are fixing mistakes or abandoning correct answers. We introduce a controlled two-pass audit that holds the question, the evidence, and the model's i…

🅲 hạng C
26
More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs
📄 Paper arXiv cs.AI 1 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.17610v1 Announce Type: new Abstract: Evaluations of multi-agent language models often compare communicating architectures against a single greedy pass. This practice confounds coordination with sample multiplicity and inference compute. We synthesize nine primary empi…

🅲 hạng C
26
Where the Savings Go: The Limits of Hiding Cross-Tenant Cache Hits in LLM Serving
📄 Paper arXiv cs.CR 22 giờ trước

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…

🅲 hạng C
26
SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations
📄 Paper HF Daily Papers 3 ngày trước

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…

🅲 hạng C
24
Co-Sight Harness: Externalized Control Assets and Deterministic Enforcement for Long-Horizon Business Agents
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.17696v1 Announce Type: new Abstract: Long-horizon business workflows fail in two ways: errors accumulate as a chain of activities lengthens, and the knowledge an activity needs is written in a different vocabulary from the user's request. We study whether such workflo…

🅲 hạng C
24
Veritas: A Verifier Generation Harness for Agent Tasks
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.13336v1 Announce Type: cross Abstract: The effectiveness of a self-improving system relies heavily on the quality of its verifier, which judges the outcome of each improvement round. However, the verifiers of most tasks are written by hand, which is expensive and does…

🅲 hạng C
23
When Does Confidence Reveal Problem Difficulty?
📄 Paper arXiv cs.AI 22 giờ trước

arXiv:2611.19173v1 Announce Type: new Abstract: While confidence signals are commonly evaluated for their ability to predict a model's own correctness, their relationship with problem difficulty remains less understood. In this work, we investigate a wide range of confidence-rel…

🅲 hạng C
23
Memory Safety Isn't All You Need: Code Reuse Attacks in Memory Safe Languages
📄 Paper arXiv cs.CR 22 giờ trước

arXiv:2611.18910v1 Announce Type: new Abstract: Memory safety rules out classical code reuse attacks that rely on arbitrary memory corruption, but does not eliminate code reuse altogether. Attacks such as object injection, prototype pollution, class pollution, DOM clobbering, an…

🅲 hạng C
22
Advancing Quantization for R&R Models with Microscaling Formats
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.17501v1 Announce Type: new Abstract: Recommendation and Ranking (R&R) models, particularly in digital advertising, require massive inference throughput but exhibit extreme sensitivity to precision loss. Unlike Large Language Models (LLMs) that frequently tolerate quan…

🅲 hạng C
22
Pairing AIS with RF: Analysis of a Markovian Approach for Maritime Data Fusion
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.18563v1 Announce Type: cross Abstract: Monitoring maritime activities is important for safety and security, particularly for detecting illegal activities, but remains challenging due to the size and complexity of the maritime domain. The Automatic Identification Syste…

🅲 hạng C
21
DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images
📄 Paper HF Daily Papers 2 ngày trước

Can a vision-language model look at a picture of a chain reaction and tell what will happen? Recent multimodal models describe scenes fluently and solve textbook physics problems, which suggests they should also predict how a scene of ramps, ledges, pendulums, seesaws and dominoe…

🅲 hạng C
20
MEM-SQL: Memory-Empowered Text-to-SQL
📄 Paper HF Daily Papers 5 ngày trước

Text-to-SQL systems translate natural language questions into SQL queries over increasingly complex databases. However, widely used benchmarks evaluate questions independently, overlooking settings where earlier queries over the same database can supply joins or calculations for …

🅲 hạng C
20
WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents
📄 Paper HF Daily Papers 5 ngày trước

Web agents powered by large language and vision-language models are increasingly applied to realistic browser work that spans heterogeneous applications, multimodal content, and stateful workflows. However, existing reproducible web-agent benchmarks cover only a small number of w…

🅲 hạng C
20
When Should Semantic Priors Enter Partially-Identified Causal Discovery?
📄 Paper arXiv cs.AI 4 ngày trước

arXiv:2611.14736v1 Announce Type: new Abstract: Observational causal discovery often leaves causal di- rections unresolved or unstable. Large language mod- els (LLMs) can provide semantic information to resolve these directions, but incorrect proposals can exclude the true causa…

🅲 hạng C
20
Your Secrets Are Showing: Deep Image Hiding Models Are Surprisingly Easy to Attack
📄 Paper arXiv cs.CR 4 ngày trước

arXiv:2611.15583v1 Announce Type: new Abstract: In this work, we ask whether an attacker can go beyond detecting a hidden image and tell what it depicts, even without knowing which model hid it. We show that, for deep image hiding, this is surprisingly easy. To test this, we bui…

🅲 hạng C