cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5461, 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 6 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 6 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 6 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 6 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
Compositional Exploits in Autonomous Coding Agents: Attack Mechanics and Ephemeral Defense
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.19764v1 Announce Type: new Abstract: Autonomous coding agents (such as Antigravity, Claude Code, Cursor, and OpenHands) rely on third-party tools to inspect files, run commands, and call external APIs. Today's security auditors evaluate these tools almost entirely in …

🅲 hạng C
30
Beyond the Patch: Reconstructing an Incomplete-Fix Patch Bypass in LLM Agent Frameworks with Control-Gated, Benign Probes
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.20514v1 Announce Type: new Abstract: Replaying a vulnerability's original proof-of-concept after patching tests whether its reported trigger remains reproducible, but does not establish that the underlying security invariant holds on other code paths. We present a ben…

🅲 hạng C
30
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 6 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
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
Understanding Users' Security, Privacy, and Trust Concerns in Healthcare AI Systems
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.20223v1 Announce Type: new Abstract: Artificial intelligence is increasingly integrated into healthcare systems, from clinical information retrieval to workflow automation and decision support, which introduces new security, privacy, and trust risks with direct implic…

🅲 hạng C
28
ATLAS-Finance: Benchmarking AI Agents in Realistic Banking Environments
📄 Paper arXiv cs.AI 6 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
Readie: Low-Latency Code Sandboxes for AI Agents
📄 Paper arXiv cs.AI 6 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
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
28
LuthorSQL: A One-Pass Text-to-SQL Model as System 1 for a Slower LLM Agent
📄 Paper HF Daily Papers 5 ngày trước

Frontier LLM agents that query databases with tools are among the most accurate text-to-SQL systems, but per-query calls to a hosted model are slow, costly, and expose sensitive organizational queries to external APIs. For example, a Claude Opus 5.5 agent serving 10,000 queries a…

🅲 hạng C
27
FastFrames: Video Generation at Interactive Latency
📄 Paper HF Daily Papers 1 ngày trước

Autoregressive video diffusion models generate frames based on new observations and inputs, making them a promising medium for interactive visual experiences. However, existing models are orders of magnitude too slow for fluid interaction. This paper introduces FastFrames, a fami…

🅲 hạng C
27
LLMs as Validators for Cross-Chain Bridges: Evaluating Source-Level and Transaction-Level Attack Detection on Solana
📄 Paper arXiv cs.CR 6 giờ trước

arXiv:2611.21777v1 Announce Type: new Abstract: Cross-chain bridges have suffered substantial asset losses due to vulnerabilities in their on-chain programs. On Solana, missing validation checks can enable exploits even when the underlying blockchain operates correctly. The abil…

🅲 hạng C
27
Threat Landscape of Vibe Coding and the Road to Secure Autonomy
📄 Paper arXiv cs.CR 6 giờ trước

arXiv:2611.21822v1 Announce Type: new Abstract: Vibe coding is reshaping software development, enabling faster implementation and allowing individuals with limited programming experience to describe requirements in natural language while AI agents write, test, and deploy the cod…

🅲 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 2 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
25
Securing Multi-Agent Systems by Design
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2611.17883v1 Announce Type: new Abstract: Multi-agent systems solve complex tasks by decomposing them into subtasks, delegating the subtasks to agents, and aggregating the agents' responses using an aggregation rule. Malicious agents can manipulate the final solution by pr…

🅲 hạng C