cập nhật 11 phút trước

⏱ Độ trễ thật của tab này: trung bình 7.2 giờ sau khi CVE được công bố (n = 5393, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

32
K2-Horizon: A Frontier Fleet of Open Source Language Models
📄 Paper HF Daily Papers 1 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
32
Mem2Fair: Online Fairness Control for Text-to-Video Generation via Fair Memory
📄 Paper arXiv cs.AI 9 giờ 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
32
Agent-ZTA: A chain-Aware Zero Trust Model for Bidirectional Security-State Propagation and Runtime Containment in Multi-Agent Delegation
📄 Paper arXiv cs.CR 9 giờ 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
32
VAST: Compiling Grounded Vulnerability Scenarios into Verifiable, Multi-Step Environments for Evaluating LLM Red-Team Agents
📄 Paper arXiv cs.CR 9 giờ 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
32
Beyond the Patch: Reconstructing an Incomplete-Fix Patch Bypass in LLM Agent Frameworks with Control-Gated, Benign Probes
📄 Paper arXiv cs.CR 9 giờ 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
Vision-as-a-Tool: Visual Harness for Multimodal Agentic Coding
📄 Paper arXiv cs.AI 1 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
30
Aligning AI Teams
📄 Paper arXiv cs.AI 1 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
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
29
Auditable Authorization for LLM Agents: Empirical Evidence Across Model, Harness, and Workflow Layers
📄 Paper arXiv cs.AI 9 giờ trước

arXiv:2611.19237v1 Announce Type: new Abstract: Human approval provides effective control only if rejected work stops and authorized work completes. We formalize refusal safety and bounded authorization completeness, and audit three execution boundaries: the model selects a call…

🅲 hạng C
29
A Push Down the Mountain: Framing Effects and Internal State Interventions on Collusive Behavior in a Long-Horizon LLM Agent
📄 Paper arXiv cs.AI 1 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
29
What LLM Agents See and What Users Say
📄 Paper arXiv cs.AI 1 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
29
Condensing Law of Security Information
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.17918v1 Announce Type: new Abstract: Scaling laws indicate that the generalization error of a large language model (LLM) decreases monotonically with model size once data is sufficient, and the corollary that larger models outperform smaller ones is now widely accepte…

🅲 hạng C
👁 Trúng danh sách theo dõi: kw:zero-day
28
Aligning AI Teams
📄 Paper HF Daily Papers 4 ngày trước

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 transfer to multi-agent LLM teams. We focus on two sof…

🅲 hạng C
28
Agents Cannot Hand Over What They Have Not Yet Understood
📄 Paper arXiv cs.AI 9 giờ trước

arXiv:2611.18642v1 Announce Type: new Abstract: Agents that work beyond a single context window, or in teams, hand their work to a successor as a short written summary. Evaluation has focused on whether an agent can solve a task, and relatively little is known about how much of …

🅲 hạng C
28
SPLICE: Structured Prompt Local Iterative Combinatorial Evolution
📄 Paper arXiv cs.AI 9 giờ trước

arXiv:2611.18883v1 Announce Type: new Abstract: Natural language optimization (NLO) improves an agent by having a model critique and rewrite its natural language policy parameters: system prompts, tool instructions, reasoning directives, few-shot demonstrations. These artifacts …

🅲 hạng C
28
FundingClaw: Automated Grant Proposal Writing Agents System
📄 Paper arXiv cs.AI 9 giờ trước

arXiv:2611.19157v1 Announce Type: new Abstract: Grant proposal writing remains a manual, labor-intensive bottleneck: proposals must satisfy rigid, agency-specific templates, and the same intellectual content must be repeatedly re-encoded into incompatible formats across funding …

🅲 hạng C
28
LuthorSQL: A One-Pass Text-to-SQL Model as System 1 for a Slower LLM Agent
📄 Paper HF Daily Papers 4 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
28
Experience-Handoff Reinforcement Learning for Recursive Self-Improvement
📄 Paper HF Daily Papers 5 ngày trước

It is common to train Large Language Models (LLMs) for agentic tasks with Reinforcement Learning (RL) from scalar rewards. However, this throws away the fine-grained information about the environment that the agent experienced during the trial (e.g., error logs). To utilize this …

🅲 hạng C