TSR · The desk
Science · 11 October 2026
Articles in this category in 11 October 2026.
TSR Desk · science · 11 October 2026, 01:00 UTC
How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and DefenseTSR Desk · science · 11 October 2026, 01:00 UTC
From Prompting to Composing: A Spatial Canvas Interface for Poster GenerationTSR Desk · science · 11 October 2026, 01:00 UTC
AI-Based On-Board Maritime Object Detection for Earth Observation Payload Data Reduction onTSR Desk · science · 11 October 2026, 01:00 UTC
Salesforce Koa: An Enterprise Language Model for Agentic Tool UseTSR Desk · science · 11 October 2026, 01:00 UTC
Learning to Orchestrate Evolutionary Search: Progression-Aware Deep Reinforcement Learning forTSR Desk · science · 11 October 2026, 01:00 UTC
Large Language Model Turnover Undermines Screening for Artificial Intelligence-AssistedTSR Desk · science · 11 October 2026, 01:00 UTC
Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with GuardTSR Desk · science · 11 October 2026, 01:00 UTC
Visible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects inTSR Desk · science · 11 October 2026, 01:00 UTC
Workerville: Towards an Organizational Behavior Account of Agent SafetyTSR Desk · science · 11 October 2026, 01:00 UTC
Searching for "Harmful Refusal": A Psychometric Audit of an AI Safety BenchmarkTSR Desk · science · 11 October 2026, 01:00 UTC
Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing MethodologyTSR Desk · science · 11 October 2026, 01:00 UTC
Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable WorldsTSR Desk · science · 11 October 2026, 01:00 UTC
VibeEdit: Image Editing with Canvas InstructionsTSR Desk · science · 11 October 2026, 01:00 UTC
EvoKnow: Continual Knowledge Evolution for AI-Generated Image DetectionTSR Desk · science · 11 October 2026, 01:00 UTC
VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding AgentsTSR Desk · science · 11 October 2026, 01:00 UTC
Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives