Reproducibility is not construct validity: LLM measurement of institutionally situated communication
Research
Research News
New papers, breakthroughs and academic AI research
TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives
Research
Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems
Research
Dual-Axis Policy Optimization for LLM Agents: Bayesian Feedback Attribution and Trajectory Mass Normalization
Research
Federated Learning Framework for Privacy-Preserving Kidney Stone Detection
Research
Form Over Content In Gradient-Based Data Attribution Methods
Research
Chain-of-Thought Entropy as a Reliability Signal: A Preregistered Reproduction
Research
Beyond Depth Truncation: Controlled Evaluation of Depth Utilization in Recursive Language Models
Research
GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model
Research
A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents
Research
Region-Level Policy Optimization for Fine-grained MLLM Perception
Research
MaskHarness-WAM: Instance-Grounded Harnessing for Long-Horizon Robot Manipulation
Research