Search: “llm”

arXiv:2604.09963v1 Announce Type: cross Abstract: Microreboot enables fast recovery by restarting only the failing component, but in modern microservices naive restarts are unsafe: dense dependencies

arXiv:2603.09172v4 Announce Type: replace-cross Abstract: We present improved lower bounds for seven classical Ramsey numbers: mathbf{R}(3, 13) is increased from 60 to 61, mathbf{R}(3, 18) from 99 to

arXiv:2406.05358v3 Announce Type: replace Abstract: Intensity control is a class of continuous-time dynamic optimization problems with many important applications in Operations Research including queu

arXiv:2410.13987v3 Announce Type: replace Abstract: Answering complex real-world questions in the medical domain often requires accurate retrieval from medical Textual Knowledge Graphs (medical TKGs),

arXiv:2604.09860v1 Announce Type: cross Abstract: The pursuit of general-purpose robotics has yielded impressive foundation models, yet simulation-based benchmarking remains a bottleneck due to rapid

arXiv:2604.11037v1 Announce Type: cross Abstract: Multi-step agentic reinforcement learning benefits from fine-grained credit assignment, yet existing approaches offer limited options: critic-free met

☁️ Salesforce tools now in Fleet One of the most requested features we've gotten, and it's now a first-class supported tool in Fleet! Just sign in with your Salesforce account, and start using it imme

arXiv:2604.10299v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attack

arXiv:2604.09890v1 Announce Type: cross Abstract: Across multiple language pairings (English o {Spanish, French, German, Mandarin, Japanese, Urdu, Cantonese}), we find reasoning errors in translation.

arXiv:2604.10027v1 Announce Type: new Abstract: Large language models (LLMs) suffer from hallucination and context forgetting. Prior studies suggest that attention drift is a primary cause of these pr

arXiv:2409.02231v5 Announce Type: replace-cross Abstract: We show that large language model (LLMs) can be transformed via supervised fine-tuning (SFT) of engineered prompts into SmileyLlama for explor

arXiv:2509.04123v2 Announce Type: replace Abstract: Text-to-story visualization is challenging due to the need for consistent interaction among multiple characters across frames. Existing methods stru

arXiv:2604.11364v1 Announce Type: new Abstract: The two most influential cognitive architecture frameworks for AI agents, CoALA [21] and JEPA [12], both lack an explicit Knowledge layer with its own p

arXiv:2604.09780v1 Announce Type: new Abstract: Mixture of Experts (MoEs) are now ubiquitous in large language models, yet the mechanisms behind their 'expert specialization' remain poorly understood.

arXiv:2604.09911v1 Announce Type: cross Abstract: In the psychological literature the term `general intelligence' describes correlations between abilities and not simply the number of abilities. This

arXiv:2604.11435v1 Announce Type: cross Abstract: Character description generation is an important capability for narrative-focused applications such as summarization, story analysis, and character-dr

This is why we released liteparse :) Free, open-source, designed for agents. Natively supports OCR / screenshotting for deeper visual understanding in a document when needed. @kepano I just tried it t

arXiv:2604.11544v1 Announce Type: cross Abstract: Structured memory representations such as knowledge graphs are central to autonomous agents and other long-lived systems. However, most existing appro

arXiv:2505.11737v4 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) have demonstrated impressive capabilities, their output quality remains inconsistent across various applica

arXiv:2604.10530v1 Announce Type: cross Abstract: How software developers interact with Artificial Intelligence (AI)-powered tools, including Large Language Models (LLMs), plays a vital role in how th

arXiv:2604.11193v1 Announce Type: new Abstract: Multi-hop Knowledge Graph Question Answering (KGQA) requires coherent reasoning across relational paths, yet existing methods often treat each reasoning

arXiv:2405.09866v2 Announce Type: replace-cross Abstract: In recent years, novel communication strategies have emerged to face the challenges that the increased number of connected devices and the hig

arXiv:2602.14200v4 Announce Type: replace Abstract: Time Series Language Models (TSLMs) are emerging as unified models for reasoning over continuous signals in natural language. However, long-context

arXiv:2505.17682v2 Announce Type: replace-cross Abstract: Predicting user behavior is essential for intelligent assistant services, yet deep learning models often struggle to capture long-tailed behav

arXiv:2502.04501v3 Announce Type: replace Abstract: Large language models achieve state-of-the-art performance but are increasingly costly to fine-tune. Prompt tuning is a parameter-efficient fine-tun

arXiv:2604.11036v1 Announce Type: cross Abstract: Scientific fact-checking is vital for assessing claims in specialized domains such as biomedicine and materials science, yet existing systems often ha

arXiv:2512.17270v2 Announce Type: replace-cross Abstract: Role-playing models (RPMs) are widely used in real-world applications but underperform when deployed in the wild. This degradation can be attr

Version numbers are not a very useful way to understand model ability gains at this stage. Unfortunately that means that if you aren’t following closely, you would expect that 5.4 is a small gain over

arXiv:2604.10533v1 Announce Type: cross Abstract: Conventional Vision-and-Language Navigation (VLN) benchmarks assume instructions are feasible and the referenced target exists, leaving agents ill-equ

arXiv:2604.09558v1 Announce Type: cross Abstract: With the widening gap between compute and memory operation latencies, data movement optimizations have become increasingly important for DNN compilati

Cursor AI shared observations on X validating that multi-agent architectures demonstrate superior performance when tackling novel problems that fall outside the distribution of training data. The post

arXiv:2604.10062v1 Announce Type: new Abstract: We study reward poisoning attacks in reinforcement learning (RL), where an adversary manipulates rewards within constrained budgets to force the target

arXiv:2604.11663v1 Announce Type: new Abstract: Large Language Models (LLMs) have been shown to generate harmful content. However, the underlying causes of such behavior remain under explored. We prop

arXiv:2604.10079v1 Announce Type: new Abstract: Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent fa

arXiv:2604.10968v1 Announce Type: new Abstract: Most conversational agents (CAs) are designed to satisfy user needs through user-driven interactions. However, many real-world settings, such as academi

arXiv:2604.08890v1 Announce Type: cross Abstract: Modeling causal relationships in graph representation learning remains a fundamental challenge. Existing approaches often draw on theories and methods

arXiv:2509.26435v2 Announce Type: replace-cross Abstract: Controllable summarization moves beyond generic outputs toward human-aligned summaries guided by specified attributes. In practice, the interd

AgentZ is a locally-run, SOC (Security Operations Center) level AI agent built on top of Ollama, designed to assist with cybersecurity tasks such as threat analysis, alert triage, and incident respons

Ethan Mollick, a prominent researcher and commentator on AI, expresses cautious optimism about the trajectory of AI-powered coding tools, acknowledging a scenario where increasingly capable coding ass

arXiv:2604.09364v1 Announce Type: cross Abstract: When a Vision-Language Model (VLM) sees a blue banana and answers 'yellow', is the problem of perception or arbitration? We explore the question in te

As AI agents accelerate coding, what is the future of software engineering? Some trends are clear, such as the Product Management Bottleneck, referring to the idea that we are more constrained by deci

As I look at some of the replies (which are startlingly human, whats up with X?), it appears a lot of the concern is that Mythos was presented as some magic leap. I didn't read Anthropic's announcemen

arXiv:2604.08867v1 Announce Type: cross Abstract: Audio has rapidly become a primary interface for foundation models, powering real-time voice assistants. Ensuring safety in audio systems is inherentl

Vercel has introduced a 'Copy-to-Prompt' feature for Feature Flags, allowing developers to easily copy flag configurations and instructions directly into AI prompts. This functionality streamlines the

arXiv:2604.08851v1 Announce Type: new Abstract: While significant work has been done on personality recognition, the lack of multilingual datasets remains an unresolved challenge. To address this, we

Ethan Mollick shared a post on X expressing frustration that a piece of content—likely a documentary or documentary-style video—was automatically or incorrectly labeled as 'made with AI.' The post hig