cập nhật 50 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.7 giờ sau khi CVE được công bố (n = 5162, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
Do LLM Agents Still Need to Be Told How to Self-Improve?
📄 Paper HF Daily Papers 3 ngày trước

LLM agents increasingly drive their own learning. Self-improvement methods delegate various components of model optimization to the models themselves. As models become more capable, this motivates a basic question: do these increasingly capable models still need us to specify how…

🅲 hạng C
28
Pandora's Toolbox Or Why Agent Safety Cannot Be Verified
📄 Paper arXiv cs.AI 12 giờ trước

arXiv:2611.25325v1 Announce Type: new Abstract: Present artificial intelligence agents are constructed by means of a coupling between a fixed language model with a general computing device. We show that this coupling makes safety undecidable. In particular, we show that given so…

🅲 hạng C
28
When Should a Voice Agent Speak? End-of-Turn Detection in Turkish
📄 Paper arXiv cs.AI 12 giờ trước

arXiv:2611.25489v1 Announce Type: new Abstract: A voice agent that waits for a fixed silence before replying either interrupts users who pause mid-utterance or responds late to users who have finished. This study examines the decision at the onset of silence, using turn ends and…

🅲 hạng C
27
Staged Semantic Distillation: Preserving Free-Form Semantics in a Low-Compute Non-LLM Surrogate of a Staged LLM Agent
📄 Paper arXiv cs.AI 3 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
27
Posterior Matching Distillation
📄 Paper HF Daily Papers 1 ngày trước

Diffusion distillation accelerates image and video generation by compressing a pretrained teacher's iterative sampling process into a few network evaluations. Distribution-based methods achieve this by matching the student's output distribution to the teacher's. This matching is …

🅲 hạng C
27
Condensing Law of Security Information
📄 Paper arXiv cs.CR 4 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
25
What Does an Agent Need? Bundle-Aware Agent Resource Composition
📄 Paper arXiv cs.AI 2 ngày 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
25
GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.23476v1 Announce Type: new Abstract: Autonomous AI agents pair a frozen base model with an editable harness of prompts, skills, tool rules, and memory. Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing withou…

🅲 hạng C
25
Agentic On-Policy Distillation Implicitly Reshapes LLMs' ReAct Patterns
📄 Paper arXiv cs.AI 3 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.19244v1 Announce Type: new Abstract: On-policy distillation (OPD) transfers specialized capabilities to language-model agents, but its cross-domain effects on interaction remain unclear. We investigate how OPD reshapes ReAct interaction patterns across mathematics, AL…

🅲 hạng C
24
More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs
📄 Paper arXiv cs.AI 4 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
23
RICoT: Recurrent Interleaved Chain-of-Thought for Page Stream Segmentation
📄 Paper HF Daily Papers 3 ngày trước

Large language models (LLMs) have renewed interest in Page Stream Segmentation (PSS), splitting a multi-page file into its constituent documents. Yet published LLM methods still frame the task as boundary classification over one or a few neighboring pages, and commercial document…

🅲 hạng C
23
PGPO: Prototype-Guided Progressive Obfuscation for Privacy-Preserving LLM-Enhanced Recommendation
📄 Paper arXiv cs.CR 1 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.23236v1 Announce Type: cross Abstract: LLM-enhanced recommender systems encode item side information into semantic embeddings, but these embeddings may leak sensitive textual attributes through inversion attacks. Existing input-side defenses rely on trusted collection…

🅲 hạng C
22
PULSAR-V: I/O-Aware Post-Update Attestation for RISC-V
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.24135v1 Announce Type: new Abstract: Post-update attestation proves that a device installed the intended firmware, not that the image stayed protected until the report was signed. In a multi-master SoC, a master outside the attested processor can corrupt update-critic…

🅲 hạng C
22
Online Mistake Detection in Instruction-Conditioned Procedural Video
📄 Paper HF Daily Papers 1 ngày trước

An assistant monitoring a person performing a procedure is most useful when it can detect mistakes while there is still time to recover. This requires judging actions against task instructions as the video unfolds, identifying the attempted step, locating it in time, and assessin…

🅲 hạng C
22
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
21
LoCaR: Localized Canvas Retrieval With Frozen Vision-Language Model
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.22131v1 Announce Type: new Abstract: Whole image embeddings can under represent small objects and local attributes that distinguish relevant images for localized queries. We present LoCaR, a training free framework for localized text to image retrieval with frozen vis…

🅲 hạng C