cập nhật 3 phút trước

⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5349, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

30
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
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

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
24
Interpreting Coding Agents Through Their Behavioral Trajectories
📄 Paper HF Daily Papers 5 ngày trước

Standard coding-agent benchmarks primarily evaluate binary task success, treating execution as a black box and obscuring the behaviors that produce those outcomes. We analyze a large corpus of 143,209 execution trajectories from 125 agent configurations spanning 117 unique models…

🅲 hạng C
23
When Is Proof-Step Verification Worth Its Cost? Operating Requirements of Certify-or-Decline Verification for Open-Weight Mathematical Reasoning
📄 Paper arXiv cs.AI 4 ngày trước

arXiv:2611.14794v1 Announce Type: new Abstract: Proof-step verification rewrites a solver's answer into typed steps and uses LLM judges to certify or decline. We evaluate this pipeline on open-weight models across GPQA, AIME-2025, and a MATH-500 subset. Certification raises answ…

🅲 hạng C
23
VRMaaS: Verifiable Reward-Model-as-a-Service for Trustworthy LLM Alignment
📄 Paper arXiv cs.CR 4 ngày trước

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…

🅲 hạng C
23
RuralShield: Super Intelligence-Assisted Security Triage and Serverless Infrastructure for Resource-Constrained Healthcare
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.17887v1 Announce Type: new Abstract: Resource-constrained healthcare providers must connect cloud security controls to an operational response process. Introducing language-model assessments adds an authorization problem: a recommendation must be converted into a perm…

🅲 hạng C
21
IoTPwnBench: A Synthetic Benchmark for IoT Firmware Security Analysis
📄 Paper arXiv cs.CR 4 ngày trước

arXiv:2611.15316v1 Announce Type: new Abstract: Building and evaluating security tools for IoT firmware requires targets whose weaknesses are known in ad- vance and can be reproduced in a running device. Two problems remain: (1) firmware collected from real-world products provid…

🅲 hạng C