cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5441, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
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
25
Where Autonomy Belongs: A Separation of Powers for Agentic Program Evolution
📄 Paper arXiv cs.AI 6 ngày trước

Paper đề xuất 'tách quyền lực' (separation of powers) cho agentic program evolution với 3 vai trò: govern (điều hướng từ bằng chứng), propose (sinh ứng viên), judge (validate fitness). Thống kê thấy hệ thống controller-centric và agent-centric đều lệch bên và tổn phí tài nguyên khi agent tự làm cả hai. Tham khảo khi design kiến trúc evolution pipeline cho code agent.

🅲 hạng C
25
Securing Multi-Agent Systems by Design
📄 Paper arXiv cs.CR 3 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
24
A Reinforcement Learning Method to Navigate SMEFT Operator Space
📄 Paper HF Daily Papers 3 ngày trước

In particle physics, discrepancies between experimental measurements and Standard Model (SM) predictions are commonly interpreted within new theoretical models. In this context, the Standard Model Effective Field Theory (SMEFT) provides a general framework encompassing a broad cl…

🅲 hạng C
24
Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2510.10140v3 Announce Type: replace-cross Abstract: Deep learning-based weather forecasting (DLWF) models leverage past weather observations to generate future forecasts, supporting a wide range of downstream applications, including tropical cyclone (TC) prediction. In thi…

🅲 hạng C
23
Invariant-Aware Harness Enforcement to Protect LLM Agents from Silent API Failures
📄 Paper HF Daily Papers 3 ngày trước

LLM agents answer questions by calling APIs and trusting the results. An API can fail silently. It ignores part of a request, such as a misnamed filter, yet returns HTTP 200 and a plausible but wrong result. Current fixes, such as checklists, reviewer models and LLM judges, ask t…

🅲 hạng C
23
Language Models Can Rewrite Their Own Weights
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.21885v1 Announce Type: new Abstract: Language models are trained once, frozen and deployed: improving one again takes another training run, and a prompt, a scaffold or extra computation at inference is gone once the task ends. A frontier model has been shown to edit t…

🅲 hạng C
23
Reconfiguring Procedural Knowledge for Compositional Robot Skill Adaptation
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.22174v1 Announce Type: new Abstract: General-purpose behavior models increasingly internalize broad procedural knowledge during training, making their adaptation to new goals and skill interfaces less a problem of learning entirely new behaviors than of reconfiguring …

🅲 hạng C
23
When Is Proof-Step Verification Worth Its Cost? Operating Requirements of Certify-or-Decline Verification for Open-Weight Mathematical Reasoning
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.14794v1 Announce Type: new Abstract: Proof-step verification rewrites a solver's answer into typed steps and uses LLM judges to certify or decline. We evaluate this pipeline on open-weight models across GPQA, AIME-2025, and a MATH-500 subset. Certification raises answ…

🅲 hạng C
23
VRMaaS: Verifiable Reward-Model-as-a-Service for Trustworthy LLM Alignment
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.14984v1 Announce Type: new Abstract: Reward models (RMs) are increasingly deployed as service components in LLM alignment pipelines, where payment, audit, moderation, and governance workflows act on the scores they return. An inference proof alone does not show whethe…

🅲 hạng C
22
Agent-Guided Process Verification for Mathematical Self-Correction
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.19122v1 Announce Type: new Abstract: Large language models have made substantial progress in mathematical reasoning, yet in complex multi-step reasoning, an error at any step may propagate along an incorrect path, and the resulting solution may omit necessary branches…

🅲 hạng C
22
When Does Confidence Reveal Problem Difficulty?
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.19173v1 Announce Type: new Abstract: While confidence signals are commonly evaluated for their ability to predict a model's own correctness, their relationship with problem difficulty remains less understood. In this work, we investigate a wide range of confidence-rel…

🅲 hạng C
21
LoRAWeaver: Directional Adapter Routing in LoRA Representation Space
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.17340v1 Announce Type: new Abstract: Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-specific LoRA adapters. This pool complic…

🅲 hạng C
21
Online Allocation with Differential Privacy
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.17554v1 Announce Type: new Abstract: We study private online allocation problems, where allocation decisions must satisfy differential privacy (DP) to protect sensitive user information while optimizing performance under limited resources. We first formalize different…

🅲 hạng C
21
RuralShield: Super Intelligence-Assisted Security Triage and Serverless Infrastructure for Resource-Constrained Healthcare
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.17887v1 Announce Type: new Abstract: Resource-constrained healthcare providers must connect cloud security controls to an operational response process. Introducing language-model assessments adds an authorization problem: a recommendation must be converted into a perm…

🅲 hạng C
21
DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images
📄 Paper HF Daily Papers 3 ngày trước

Can a vision-language model look at a picture of a chain reaction and tell what will happen? Recent multimodal models describe scenes fluently and solve textbook physics problems, which suggests they should also predict how a scene of ramps, ledges, pendulums, seesaws and dominoe…

🅲 hạng C
21
AuXSpec: Learning to Autoformalize Program Specifications via Executable Postconditions
📄 Paper HF Daily Papers 3 ngày trước

Formal specifications define intended program behavior and underpin verification, but writing them in theorem provers such as Lean is slow and expertise-intensive, making specification a major bottleneck to scaling formally correct code. Autoformalization from natural-language pr…

🅲 hạng C
20
Self-Improvement Memory Enables Continual Recursive Self-Improvement
📄 Paper HF Daily Papers 6 ngày trước

Harness optimization is often studied with a fixed policy model and benchmark. When either changes, the optimizer must decide which parts of an evolved harness to reuse or revise, but the harness alone may not explain why earlier edits were made or how they performed. In this wor…

🅲 hạng C
20
PaperCritic: Training AI Reviewers to Assess the Soundness of Papers
📄 Paper HF Daily Papers 6 ngày trước

As AI conference submissions grow rapidly, AI reviewers are being considered as an alternative. However, simply imitating human reviewing is problematic because reviewing serves multiple purposes, including evaluating papers' soundness, interestingness, and clarity, the last two …

🅲 hạng C
20
Stress-Testing Sandbagging Detection Under Adaptive Attack
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.14950v1 Announce Type: new Abstract: Developers, auditors and researchers read evaluation scores as evidence of what a model can do. A model that sandbags, scoring low on purpose while keeping the capability, turns a low score into false reassurance. Sandbagging detec…

🅲 hạng C