Jiahao Qiu

Alita-G: Self-Evolving Generative Agent for Agent Generation

CubeBench: Diagnosing Interactive, Long-Horizon Physical Intelligence under Partial Observations

Teaching Language Model to Act Efficiently

Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution

On the Role of Preference Variance in Preference Optimization

On Path to Multimodal Historical Reasoning: HistBench and HistAgent

AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes

ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs

Collab: Controlled Decoding using Mixture of Agents for LLM Alignment