11 posts published in the last hour
- 07:32CuBEs: Culturally-Situated Behavioral Evaluations and the Limitations of Culture-Blind LLM Judges
- 07:32Time Series Forecasting Benchmarks Need Scenario-Grounded Stress Testing
- 07:32VERSE: Verified Self-Evolving Optimizer for Agent Harnesses
- 07:32Lost in the Request: How Communication Variation Disrupts Retrieval and Action in Email Agents
- 07:32Designing the Future of User Feedback for Generative AI
- 07:02Mitigating Social Sycophancy via Pluralistic Preference Optimization
- 07:02TasteBench: Multimodal Benchmark for Sensory Prediction, from Molecules to Sustainable Foods
- 07:02Open-Endedness Bench: Measuring Epistemic Process from Agent Records
- 07:02Answering clinicians’ questions over trial evidence tables with verifiable, feedback-driven language models
- 07:02Labels Override Definitions in Jev-Style Typed Decision Models
- 07:00AI News Brief Hourly Summary 2026-10-05 09h : 10 posts
