Akademik Araştırma
& Analytics.
ArXiv veritabanından canlı olarak çekilen, yapay zeka ve makine öğrenimi alanındaki en son akademik yayınları keşfedin.
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction...
SWE-Prime: Fewer Trajectories, Better Performance
To improve large language models' ability to resolve real-world software issues, prior work has focused on constructing large-scale agent trajectory datasets and performing supervised fine-tuning (SFT) on successful trajectories. However, task succes...
From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench
In real-world software development, code review typically involves iterative interactions between developers and reviewers to improve software quality, making the process costly and time-consuming. Although recent work explores large language models ...
RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution
LLM-based agents are increasingly deployed in product-level execution harnesses, where jailbreaks can trigger harmful tool use and persistent state changes, creating greater risks than unsafe text generation alone. Existing automatic red-teaming meth...
Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation
Chemical reactions are fundamentally transformations in electron space, yet most machine learning approaches model them either through \textit{de novo} generation of product molecules or through heuristic graph edits that operate directly on molecula...
Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audit
Large language model (LLM) agents in governed organizations must let the persona (instructions, tone, self-presentation) evolve freely, while keeping execution (stateful, audited work) traceable. A single trust domain does not satisfy both cheaply. W...
Beyond F1: Evaluating Coverage and Failure Recovery in AI Model Security Scanners
Static scanners are increasingly used to identify executable or otherwise unsafe content in machine- learning artifacts, yet conventional evaluation metrics characterize only cases where a scanner yields a usable security judgment. We evaluate ModelS...
Learning a Continuous Sepsis Severity Score Without Hour-by-Hour Supervision: A Two-Site Retrospective Study
Currently used sepsis severity indices rely on fixed variables and weights established decades ago, which are coarsely discretized and calibrated to a cohort that no longer reflects contemporary critical care. No alternative learned directly from pat...
Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Sampling
Friend recommendation is inherently graph-structured: the relevance of a potential connection depends on multi-hop social context rather than user attributes alone. However, deploying message-passing GNNs on a production-scale social graph with hundr...
ArXiv API Entegrasyonu
Bu sayfa doğrudan arXiv.org veritabanından veri çekmektedir. Listelenen tüm içerikler global akademik topluluk tarafından paylaşılan open-access yayınlardır.