4 papers
Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning
Guangzhi Wang, Kai Li, Yinghao Jiao +1
We propose RT (Refine Thought), a method that can enhance the semantic reasoning ability of text embedding models. The method obtains the final semantic representation by running m…
CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrieval
Guangzhi Wang, Yinghao Jiao, Zhi Liu
The central challenge of reasoning-intensive retrieval lies in identifying implicitreasoning relationships between queries and documents, rather than superficial se-mantic or lexic…
PJB: A Reasoning-Aware Benchmark for Person-Job Retrieval
Guangzhi Wang, Xiaohui Yang, Kai Li +4
As retrieval models converge on generic benchmarks, the pressing question is no longer "who scores higher" but rather "where do systems fail, and why?" Person-job matching is a dom…
Time-Scaling Is What Agents Need Now
Zhi Liu, Guangzhi Wang
Early artificial intelligence paradigms exhibited separated cognitive functions: Neural Networks focused on "perception-representation," Reinforcement Learning on "decision-making-…