Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses
Research
Research News
New papers, breakthroughs and academic AI research
EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling
Research
The AI Risk Observatory: What Can We Learn from AI Disclosures in Annual Reports About Societal Resilience?
Research
Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation
Research
SCION: Scene Composition with Instanced Neural Primitives
Research
Octrees as an Explicit 3D Language
Research
HakemBench: A Turkish Benchmark of Typed Decisions
Research
A generative-informed neuro-symbolic framework for syntactic ambiguity resolution: Evidence from Arabic DPs
Research
Overcoming Challenges of Interpretive Structural Modeling with Large Language Models
Research
Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents
Research
THPL: A Vision-to-Language Decision Support Framework for Rainbow Trout Feeding Management in RAS
Research
CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking
Research