cập nhật 6 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5267, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

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
24
Attacker Diversity Reduction in Adaptive LLM Red Teaming
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2611.19680v1 Announce Type: new Abstract: Reinforcement learning can make automated red-teaming more successful while narrowing the attacks it produces. Co-training an attacker and a defender with group-relative policy optimization (GRPO) has been reported to reduce attack…

🅲 hạng C
23
Training Language Models for Introspective Oversight
📄 Paper arXiv cs.AI 17 giờ trước

arXiv:2611.23365v1 Announce Type: new Abstract: Language models increasingly exhibit behaviors that are difficult to detect in transcripts, such as reward hacking, deception, and sycophancy. Asking the assistant follow-up questions about its actions is unreliable, since models a…

🅲 hạng C
23
HINT-WAM: Hindsight-Informed Training for World Action Models
📄 Paper HF Daily Papers 2 ngày trước

World action models (WAMs) have shown promising generalization and data efficiency in robot manipulation by coupling action generation with predictions of future visual dynamics. Translating these capabilities into reliable task execution, however, remains a challenge for existin…

🅲 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
Fast and Strong Image Protection against Diffusion Personalization
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.22494v1 Announce Type: cross Abstract: Personalized text-to-image diffusion models can reproduce a person from a handful of photographs. Image protection perturbs each image before publication so that fine-tuning on it fails, but it optimizes every perturbation from s…

🅲 hạng C
22
Evidence-Based Credit Assignment for Search-Augmented Language Models
📄 Paper HF Daily Papers 2 ngày trước cũng có trên: arXiv cs.AI

Reinforcement learning from terminal answer rewards enables search-augmented language models to interleave reasoning and retrieval without step-level annotations, yet outcome supervision assigns identical credit to every search in a trajectory regardless of whether it retrieved u…

🅲 hạng C
21
Policy Optimization With Multiple Verifiers via Pareto Rankings
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.19064v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an important approach to improving the reasoning capabilities of large language models. In tasks such as code generation and instruction following, multiple verifiers…

🅲 hạng C
21
Replay, Don't Resample: Off-Policy Consolidation of Long-Horizon RL Experts
📄 Paper HF Daily Papers 2 ngày trước

Frontier post-training follows a common recipe: train one expert per domain with reinforcement learning (RL), then consolidate the experts into one model via multi-teacher on-policy distillation (MOPD). Such consolidation is expensive: the student samples in every environment aga…

21
Regularized Score Centering
📄 Paper HF Daily Papers 4 ngày trước

Asynchronous reinforcement learning increases training throughput, but data from stale policies and numerical mismatch between training and inference can destabilize learning. To stabilize off-policy learning, score centering (SC) removes the effect of reward baselines on the exp…

🅲 hạng C