Qingyun Wu

Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning

ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems

BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute

Adaptive In-conversation Team Building for Language Model Agents

EcoAct: Economic Agent Determines When to Register What Action

Cost-Efficient Multi-Fidelity Alignment for LLMs