13 posts published in the last hour
- 09:34Finding the Right Fit: Model-Harness Interactions across Agent Tasks
- 09:34ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
- 09:33OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework
- 09:33Microsoft AI releases new transcription and text-to-speech models for voice agents
- 09:33PG-SFT: Balancing Capability Acquisition and Retention in Offline Agent Fine-Tuning
- 09:32Businesses are using more AI and paying less for it, Ramp AI Index shows
- 09:32ABDA-NL: A Natural-Language Scenario Explorer for Argument-Based Reasoning
- 09:03Kepler: Auditable World Models for ARC-AGI-3
- 09:03Learning Multiple Timescales for Goal-Conditioned Reinforcement Learning
- 09:03An Educator-Guided LLM Pedagogical Agent for Scaffolded Feedback in Conceptual Database Design
- 09:03Sapien: A Stateful Policy Engine for Autonomous AI Agents
- 09:03Don’t be fooled—LLMs don’t reason
- 09:03MemFit: Efficient Long-Term Agentic Memory
