TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts
cs.AI
Submitted: 2026-10-05
Updated: 2026-10-06
Sources
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
- HindSight: Evaluating LLM-Generated Research Ideas via Future Impact
- Measuring AI Ability to Complete Long Software Tasks
- AI Can Learn Scientific Taste
- RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts
- Proof of Time: A Benchmark for Evaluating Scientific Idea Judgments
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems