cập nhật 29 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.9 giờ sau khi CVE được công bố (n = 5185, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

30
Weighing the Envelope: Component Weight and Arbitration in Envelope-Layer Defenses for a Single LLM Agent
📄 Paper arXiv cs.CR 20 giờ trước

Bài nghiên cứu mới giới thiệu mô hình Envelope Layer cho LLM Agent, đánh giá trọng lượng các thành phần và cách giải quyết rủi ro khi công cụ MCP và bộ nhớ lâu dài đồng thời tồn tại. Điều này giúp cải thiện an toàn và giảm rủi ro lây nhiễm nội dung độc hại trong AI Agent.

🅲 hạng C
29
K2-Horizon: A Frontier Fleet of Open Source Language Models
📄 Paper HF Daily Papers 4 ngày trước

We present K2-Horizon, a fleet of six fully open language models, from a 0.9B dense model to a 375B-A23B MoE, built for general-purpose reasoning and agentic work across math and science, software engineering, deep research, office automation, and beyond. The models lead or are c…

🅲 hạng C
29
Do LLM Agents Still Need to Be Told How to Self-Improve?
📄 Paper HF Daily Papers 3 ngày trước

LLM agents increasingly drive their own learning. Self-improvement methods delegate various components of model optimization to the models themselves. As models become more capable, this motivates a basic question: do these increasingly capable models still need us to specify how…

🅲 hạng C
28
DiscoveryAgent: A Framework for Scientist-centric Agentic AI
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.21950v1 Announce Type: new Abstract: AI agents can assist scientific research, but balancing autonomous investigation with scientists' ability to inspect and redirect ongoing work remains a central design challenge. We present DiscoveryAgent, a domain-agnostic, scient…

🅲 hạng C
28
Stopping Is Not the Limit: Understanding and Eliciting Agent Capability in Long-Horizon Vulnerability Exploitation
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.22888v1 Announce Type: new Abstract: Vulnerability exploitation tests whether language model agents can develop working exploits from known software flaws. Sequential test-time scaling can improve exploitation performance, but larger budgets do not ensure sustained ex…

🅲 hạng C
28
Aligning AI Teams
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.17820v1 Announce Type: new Abstract: Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment trans…

🅲 hạng C
28
I2C-GRPO: Insight Importance Checklist for Reinforcement Learning in a Multi-Agent DDoS Alert Triage Workflow
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.17534v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used for investigative tasks over incomplete evidence, such as cybersecurity alert triage, but reinforcement learning (RL) for such tasks is difficult: intermediate steps have no v…

🅲 hạng C
27
Large Language Models for AI Infrastructure
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.19061v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to design, optimize, and operate the infrastructure behind AI training and serving, yet the literature remains fragmented across hardware design, machine learning systems, electron…

🅲 hạng C
27
CompoundingKernel: Self-Improving from Zero to First
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.19230v1 Announce Type: new Abstract: We present CompoundingKernel, a self-improving agent system that writes GPU kernels by search. As of 2026-11-11, its generated kernels rank #1 on the public L1, L2 and Quantization boards of SOL-ExecBench (NVIDIA B200). They have h…

🅲 hạng C
27
Security of Deep Research Agents: Attack Surface, Defenses, Benchmarks, and Agenda Seeding against Research Planning
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2611.20045v1 Announce Type: new Abstract: Deep research and agentic search agents autonomously retrieve content from the open web and generate reports with citations, and their outputs are often taken directly as research conclusions. This paper systematizes security resea…

🅲 hạng C
27
GRAFT: Execution-Guided Genetic Recombination for Agent Design
📄 Paper arXiv cs.AI 20 giờ trước

arXiv:2611.23509v1 Announce Type: new Abstract: Automated agent design searches for executable architectures that improve LLM-based agent performance, with evolutionary methods using language-model crossover to recombine promising mechanisms for task decomposition, model coordin…

🅲 hạng C
27
Continual Tool-Space Extension Learning for Multimodal Agents
📄 Paper arXiv cs.AI 20 giờ trước

arXiv:2611.23810v1 Announce Type: new Abstract: Multimodal agents largely rely on generic tools such as cropping, search, and code execution, leaving specialist vision models outside their tool space. However, bringing such a model into an already trained agent is not straightfo…

🅲 hạng C
27
What LLM Agents See and What Users Say
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.17639v1 Announce Type: new Abstract: Before an LLM agent cancels a reservation or deletes a folder for a user, what stops it from acting on a false assumption: what its tools show, or what the user says? In this work, we study this gap with presupposition theory from …

🅲 hạng C
26
STA: A Split Temporal Adversary Method for Evaluating Robustness of Multimodal RL-based Driving Policies
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2611.20765v1 Announce Type: new Abstract: Multimodal reinforcement learning (MRL) offers a promising paradigm for autonomous driving by jointly leveraging complementary sensor observations to learn effective decision-making policies. However, its effectiveness critically d…

🅲 hạng C
26
When Shuffling Fails: Token Recovery from Obfuscated KV Caches
📄 Paper arXiv cs.CR 20 giờ trước

arXiv:2611.24276v1 Announce Type: new Abstract: LLM serving systems store, offload, and share KV caches, exposing token-level representations to infrastructure operators and co-tenants. Shuffled obfuscation combines secret linear transforms with fresh permutations, claiming secu…

🅲 hạng C
26
What Does an Agent Need? Bundle-Aware Agent Resource Composition
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.22030v1 Announce Type: new Abstract: An agent resource's value depends on its backbone and companion resources and is known only after execution. Token-based generators remain tied to their training catalog, while independent resource scoring misses complementarities …

🅲 hạng C
26
ATLAS-Finance: Benchmarking AI Agents in Realistic Banking Environments
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.22085v1 Announce Type: new Abstract: Professional work involves under-specified assignments, where relevant information is spread across workplace applications and may conflict or change over time. To evaluate how well frontier agents can perform economically valuable…

🅲 hạng C
26
EvoDisco: Strategy Discovery for Evolving Agent Memory
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.22102v1 Announce Type: new Abstract: Large language model agents accumulate experience in memory, and how that memory evolves during interaction is as important as what it stores. Recent methods update memory online, yet both the operators that transform memory and th…

🅲 hạng C
26
Readie: Low-Latency Code Sandboxes for AI Agents
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.22171v1 Announce Type: new Abstract: From quantitative research to personal assistance, AI agents act by iteratively generating and executing code. To decouple the agent harness from code execution, many agents offload execution to dedicated systems called code sandbo…

🅲 hạng C