Yingru Li

SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

On the Scaling Flaws of Verifier-Guided Beam Search

Uncertainty-Aware Search and Value Models in LLMs

OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Scalable Exploration via Ensemble++

Scalable Exploration via Ensemble++