Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning

Anyscale and NovaSky Team Releases SkyRL tx v0.1.0: Bringing Tinker Compatible Reinforcement Learning RL Engine To Local GPU Clusters

Boosting Accuracy and Efficiency of Budget Forcing in LLMs via Reinforcement Learning for Mathematical Reasoning

TripScore: Benchmarking and rewarding real-world travel planning with fine-grained evaluation

Biomedical reasoning in action: Multi-agent System for Auditable Biomedical Evidence Synthesis

Optimizing Long-Form Clinical Text Generation with Claim-Based Rewards

The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis