LLM Judge Validation Under Sparse Overlap: From Inference to Design
Research
Research News
New papers, breakthroughs and academic AI research
What Next-Event Accuracy Cannot See: Closed-Loop Evaluation of Emergency Department Trajectory Simulators
Research
Energy-aware frugal Bayesian optimization
Research
Dude, Where's My State? Execution Information Requirements for Stateful Agents
Research
OMP-MoE: Efficient Expert Pruning for Mixture-of-Experts LLMs via Orthogonal Matching Pursuit
Research
Relic: From Multi-Agent Collaboration to Persistent Organizational Capability
Research
Working with AI: A Design Framework for Human-AI Collaboration
Research
Metro-WM: Long-Horizon Latent Planning with Realisable Sub-Goals
Research
Symmetry-quotient Flatness and Generalization
Research
COUNTERMEM: World-Model Verified Counter-Factual Memory for Language Agents
Research
EmailBench: A Benchmark for Evaluating LLM Agents on Enterprise Email and Productivity Tasks
Research
Improving Medical Calculation of LLMs with Embedded Coding
Research