cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.2 giờ sau khi CVE được công bố (n = 5285, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
DSFlow: A Neuro-Symbolic Data Workflow Agent with Statistical Diagnostic Guardrails
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.25111v1 Announce Type: new Abstract: Data science workflows often require tools that presume non-trivial technical knowledge. Large language models (LLMs) reduce this barrier, but a gap remains between flexible general-purpose agents and statistically controlled pipel…

🅲 hạng C
28
Do LLM Agents Still Need to Be Told How to Self-Improve?
📄 Paper HF Daily Papers 5 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
26
How Feedback-Free Self-Evolution Reshapes Agent Skills: A Systematic Study
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.25534v1 Announce Type: new Abstract: Agent skills are documents in which experts write down procedural knowledge, and models increasingly maintain them by rewriting them without feedback. Such rewriting could adapt a skill to the model that uses it or erode the expert…

🅲 hạng C
24
SPLICE: Structured Prompt Local Iterative Combinatorial Evolution
📄 Paper arXiv cs.AI 4 ngày 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
23
LLMs as Validators for Cross-Chain Bridges: Evaluating Source-Level and Transaction-Level Attack Detection on Solana
📄 Paper arXiv cs.CR 3 ngày 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
23
RICoT: Recurrent Interleaved Chain-of-Thought for Page Stream Segmentation
📄 Paper HF Daily Papers 5 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
22
User Perceptions of Deceptive In-Vehicle Infotainment User Interfaces
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.25195v1 Announce Type: new Abstract: Modern vehicles collect extensive data about drivers, passengers, and vehicle use, with privacy and consent decisions increasingly mediated through infotainment software. Although dark patterns have been widely studied in web, mobi…

🅲 hạng C
21
Can you make models believe false facts in the prompt?
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.23938v1 Announce Type: new Abstract: Making LLMs believe false facts is useful for alignment evaluations and for building model organisms. Previous work explored doing so with Synthetic Document Finetuning (SDF). But SDF requires fine-tuning one new model for each set…

🅲 hạng C
21
Fine-Grained Japanese Clinical Named Entity Recognition: A Controlled Comparison of BERT and Open-Weight Large Language Models
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.22219v1 Announce Type: new Abstract: Background: Generative large language models (LLMs) offer an alternative to encoder-based clinical named entity recognition (NER), but their performance on fine-grained Japanese extraction tasks and sensitivity to generation settin…

🅲 hạng C
21
A Forensic Analysis of Metadata and Information Leakage in Swedish Public Documents
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.21922v1 Announce Type: new Abstract: This study investigates metadata and structural content leakage in publicly available PDF documents from 30 Swedish public-sector authorities. Using an automated collection pipeline and ExifTool-based extraction, 2,876 documents we…

🅲 hạng C
21
Evidence-Based Credit Assignment for Search-Augmented Language Models
📄 Paper HF Daily Papers 4 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
20
Executable Archaeology: Reanimating the Logic Theorist
📄 Paper arXiv cs.AI 4 ngày trước

arXiv:2611.19167v1 Announce Type: new Abstract: The Logic Theorist (LT), created by Allen Newell, J. C. Shaw, and Herbert Simon in 1955--1956, is regarded by some as the first artificial intelligence program. It was originally simulated by hand and written in a pseudocode called…

🅲 hạng C
20
When the Spec Sheet Lies: Injection Attacks on LLM-Generated Compliance Artifacts
📄 Paper arXiv cs.CR 4 ngày trước

arXiv:2611.19090v1 Announce Type: new Abstract: As Large Language Models (LLMs) become used more commonly across a variety of fields, a growing body of research has highlighted particular concerns surrounding model security. Notably, prompt injection attacks, where malicious ins…

🅲 hạng C