cập nhật 19 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.

24
Exo: An Architecture for Self-Improving Systems at Runtime
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.00463v1 Announce Type: new Abstract: Agent harnesses govern how language models act in an environment; designing their policies by hand is difficult, while automated techniques require representative datasets and costly executions. We present Exo, an agent runtime arc…

🅲 hạng C
24
Agentic Context Management for Multi-Turn Human-AI Conversations
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.00518v1 Announce Type: new Abstract: LLMs degrade in multi-turn conversation partly because of context pollution: the model's own earlier outputs stay in context and anchor later turns, so an early misreading of the user's intent can persist after the user corrects it…

🅲 hạng C
24
Adversarial Robustness Is Not Zero-Day Generalization: A Controlled Evaluation of Flow-Based Intrusion Detectors on Corrected CIC-IDS2017
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.00713v1 Announce Type: new Abstract: Synthetic variants of known attacks, including feature-space adversarial perturbations, are sometimes used as stand-ins for unseen ("zero-day") attacks when evaluating machine-learning network intrusion detection systems (NIDS). We…

🅲 hạng C
👁 Trúng danh sách theo dõi: kw:zero-day
24
Step-Zero Attack: Agent Safety Before Observability
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.01953v1 Announce Type: new Abstract: Existing attacks and defenses for coding agents act once content enters the model context: injected text persuades the model, and guards inspect what the model reads. Yet to judge whether processing an unknown archive, network resp…

🅲 hạng C
24
DR Pixel: Page-Native Deep Research with Vision-Language Models
📄 Paper HF Daily Papers 17 ngày trước

Complex documents such as scientific papers contain rich information in tables, figures, and equations; however, existing deep research (DR) agents typically reduce papers to OCR-extracted text. We instead ask whether vision-language models (VLMs) can enable page-native deep rese…

🅲 hạng C
24
GlucoAgent: Personalized Glucose Forecasting from Multimodal Personal Context
📄 Paper arXiv cs.AI 15 ngày trước

arXiv:2611.04126v1 Announce Type: new Abstract: Continuous glucose monitors, smartwatches, meal logs, and health profiles form a rich multimodal personal context that can significantly enhance glucose forecasting. However, existing methods struggle to effectively utilize these s…

🅲 hạng C
24
Grounded but Not Immune: Confirmation Bias in Agent-as-a-judge
📄 Paper arXiv cs.AI 14 ngày trước

arXiv:2611.05662v1 Announce Type: new Abstract: Evaluating open-ended agent tasks increasingly falls to an Agent-as-a-Judge: an evaluator handed tools and the agent's full trajectory so it can verify a result against the environment. The premise is that a judge that gathers its …

🅲 hạng C
24
Securing Web Agents with the Compile-Then-Execute Paradigm
📄 Paper arXiv cs.CR 14 ngày trước

arXiv:2611.06039v1 Announce Type: new Abstract: Web agents commonly follow the ReAct paradigm, selecting each action from runtime observations that inherently mix trusted and untrusted content. This design makes their control flow vulnerable to prompt injections embedded in webp…

🅲 hạng C
24
SenTrojan: Revealing Analog Hardware Trojan Attacks on Sensors
📄 Paper arXiv cs.CR 14 ngày trước

arXiv:2611.06103v1 Announce Type: new Abstract: Sensors bridge the physical and digital worlds, making their integrity critical to cyber-physical system security. Existing sensor attacks largely exploit unintended and sensor-specific physical vulnerabilities, limiting their gene…

🅲 hạng C
24
The Two-Ledger Model: Transaction-Grain Cost Accounting for Multi-Agent AI Systems Across Clouds, Models, and Systems of Record
📄 Paper arXiv cs.AI 13 ngày trước

arXiv:2611.06989v1 Announce Type: new Abstract: Enterprises run business transactions through multi-agent AI systems spanning clouds, large language models (LLMs), orchestration harnesses, and systems of record. Finance receives AI cost only at settlement grain, aggregated by SK…

🅲 hạng C
24
Closed-Loop Agent Evaluation: Layered Measurement and Self-Calibration
📄 Paper arXiv cs.AI 13 ngày trước

arXiv:2611.07051v1 Announce Type: new Abstract: Once an agent is live, teams want to know whether it is doing its job, not just whether it throws errors. Yet most evaluation is one-off: a benchmark run, a look at traces, a single score. Its conclusions neither check themselves n…

🅲 hạng C
24
NormGym: Evaluating Normative Competence through Social Interaction
📄 Paper arXiv cs.AI 10 ngày trước

arXiv:2611.08613v1 Announce Type: new Abstract: Normative competence, the ability to infer socially enforced expectations from interaction and adjust behavior accordingly, is essential for agents operating in unfamiliar human communities. Yet existing evaluations largely test wh…

🅲 hạng C
24
Pdb or Not to Be: Comparing Debugging Interfaces With Pass$_{X}$@$k$
📄 Paper arXiv cs.AI 10 ngày trước

arXiv:2611.08666v1 Announce Type: new Abstract: Interactive debuggers are indispensable to human software development, yet coding agents overwhelmingly rely on edit-execute-observe loops, using common bash tools, test scripts, and print statements to debug via repeated shell com…

🅲 hạng C
24
CARGO: Causal Attribution and Responsibility-Guided Preventive Safe Multi-Agent Reinforcement Learning for Cooperative Driving
📄 Paper arXiv cs.AI 10 ngày trước

arXiv:2611.09139v1 Announce Type: new Abstract: This study presents Causal Attribution and Responsibility-Guided Optimization (CARGO), a multi-agent reinforcement learning framework for cooperative on-ramp merging in mixed traffic. A shared latent-context posterior and an action…

🅲 hạng C
24
Verification of Security Properties of Cryptographic Protocols
📄 Paper arXiv cs.CR 10 ngày trước

arXiv:2611.09315v1 Announce Type: new Abstract: Developing cryptographic protocols that are free from vulnerabilities is very challenging, as evidenced by numerous design flaws and implementation bugs in widely used protocols. Recent work has leveraged model checking to generate…

🅲 hạng C