REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
Paper
• 2602.14234 • Published
• 26
Chenxiao Zhao
ChenShawn
AI & ML interests
Reinforcement learning
Recent Activity
authored
a paper
8 days ago
REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents authored
a paper
8 days ago
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training authored
a paper
8 days ago
DeepEyesV2: Toward Agentic Multimodal Model Organizations
None yet