Prompt Engineering
MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills
🕵️AI Agents Content type: AcademicInvariant Gradient Alignment for Robust Reasoning Distillation
🔗LLM Workflows Content type: AcademicRREDCoT: Segment-Level Reward Redistribution for Reasoning Models
🔗LLM Workflows Content type: AcademicMIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models
🔗LLM Workflows Content type: AcademicYou Only Index Once: Cross-Layer Sparse Attention with Shared Routing
🔗LLM Workflows Content type: AcademicDeclarative Skills for AI Agents in Knowledge-Grounded Tool-Use Workflows
🕵️AI Agents Content type: AcademicSelection-Aware Diagnostics for Chain-of-Thought Answer Hijacking
🔗LLM Workflows Content type: AcademicVTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning
🔗LLM Workflows Content type: AcademicNo more posts from cwensel's subscribed feeds.