cập nhật 1 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5469, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

32
Can You Undo It? Reversibility Classes for AI Agent Actions
📄 Paper arXiv cs.AI 9 giờ trước

arXiv:2611.22075v1 Announce Type: new Abstract: Tool-using AI agents change files, databases, access rights and public information, yet permission to call a tool does not establish whether a mistake can be undone. We present Reversibility Classes, a declared five-level vocabular…

🅲 hạng C
32
Big Brains, Tiny Board: Pupavision, an Agentic Physical AI Instrument for Monitoring Drosophila Pupariation and Lifecycle Transitions
📄 Paper arXiv cs.AI 9 giờ trước

arXiv:2611.22136v1 Announce Type: new Abstract: Many biology experiments are limited by the availability and ease of use of instruments that monitor and record them. For example, the timing of pupariation in the fruit fly Drosophila melanogaster, a widely used model organism, ca…

🅲 hạng C
31
DiscoveryAgent: A Framework for Scientist-centric Agentic AI
📄 Paper arXiv cs.AI 9 giờ 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
31
Stopping Is Not the Limit: Understanding and Eliciting Agent Capability in Long-Horizon Vulnerability Exploitation
📄 Paper arXiv cs.CR 9 giờ 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
30
Mem2Fair: Online Fairness Control for Text-to-Video Generation via Fair Memory
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.19215v1 Announce Type: new Abstract: Text-to-video (T2V) generation models can produce systematically unfair demographic outcomes when prompts leave protected attributes unspecified. For example, prompts describing nurses without specifying gender may disproportionate…

🅲 hạng C
30
Agent-ZTA: A chain-Aware Zero Trust Model for Bidirectional Security-State Propagation and Runtime Containment in Multi-Agent Delegation
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.18999v1 Announce Type: new Abstract: Multi-agent systems increasingly delegate tasks and permissions across chains of autonomous agents that invoke protected tools. Although agent identities and delegated credentials may remain valid throughout a workflow, the securit…

🅲 hạng C
30
VAST: Compiling Grounded Vulnerability Scenarios into Verifiable, Multi-Step Environments for Evaluating LLM Red-Team Agents
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.19465v1 Announce Type: new Abstract: Evaluating Large Language Model (LLM) security agents requires reproducible environments whose workflow difficulty can be varied and whose failures can be diagnosed. We present VAST (Verifiable Adversarial Scenario Training & Evalu…

🅲 hạng C
29
Thinking Harder Doesn't Lead to Better Choices: Reasoning Effort Increases the Confidence but Not the Correctness of LLM Shopping Agents
📄 Paper arXiv cs.AI 9 giờ trước

arXiv:2611.22033v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as autonomous shopping agents that process multimodal product listings (consisting of visual and text data) and recommend purchases on behalf of consumers. Naturally, one might…

🅲 hạng C
29
Vision-as-a-Tool: Visual Harness for Multimodal Agentic Coding
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.17797v1 Announce Type: new Abstract: Multimodal agentic coding requires robust visual reasoning to analyze observations and evaluate generated artifacts. Current frameworks largely rely on a Thinking-with-Images paradigm, where agents depend on their intrinsic vision …

🅲 hạng C
29
Aligning AI Teams
📄 Paper arXiv cs.AI 2 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
29
Large Language Models for AI Infrastructure
📄 Paper arXiv cs.AI 1 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
29
CompoundingKernel: Self-Improving from Zero to First
📄 Paper arXiv cs.AI 1 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
29
Staged Semantic Distillation: Preserving Free-Form Semantics in a Low-Compute Non-LLM Surrogate of a Staged LLM Agent
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.19299v1 Announce Type: new Abstract: Staged LLM agents make market and social simulators realistic, but one 102-day run of a 200-agent, ten-index market simulator issues 203,100 language-model calls and returns one realization. Conventional low-compute distillation dr…

🅲 hạng C
29
Security of Deep Research Agents: Attack Surface, Defenses, Benchmarks, and Agenda Seeding against Research Planning
📄 Paper arXiv cs.CR 1 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
28
What Does an Agent Need? Bundle-Aware Agent Resource Composition
📄 Paper arXiv cs.AI 9 giờ 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
28
ATLAS-Finance: Benchmarking AI Agents in Realistic Banking Environments
📄 Paper arXiv cs.AI 9 giờ 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
28
EvoDisco: Strategy Discovery for Evolving Agent Memory
📄 Paper arXiv cs.AI 9 giờ 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
28
Readie: Low-Latency Code Sandboxes for AI Agents
📄 Paper arXiv cs.AI 9 giờ 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
28
A Push Down the Mountain: Framing Effects and Internal State Interventions on Collusive Behavior in a Long-Horizon LLM Agent
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.17515v1 Announce Type: new Abstract: Can sustained gain-loss (valence) framing sway an LLM agent toward market manipulation? We place Gemma 3 12B into the seat of a defendant in the London silver-fixing litigation, in a market simulation built from real case transcrip…

🅲 hạng C
28
What LLM Agents See and What Users Say
📄 Paper arXiv cs.AI 2 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