Qi Yi

Venues

Frequent coauthors

Papers

1. AT²PO: Agentic Turn-based Policy Optimization via Tree Search
   ACL 2026 ·

   Zefang Zong

   DBLP profile ↗ORCID search ↗
2. Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
   ACL 2026 ·

   Guanhua Huang

   DBLP profile ↗ORCID search ↗
3. Reinforcement Learning on Pre-Training Data
   ACL 2026 ·

   Siheng Li

   DBLP profile ↗ORCID search ↗
4. Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning
   ACL 2026 ·

   Ziyuan Nan

   DBLP profile ↗ORCID search ↗
5. Emergent Communication for Numerical Concepts Generalization
   AAAI 2024 ·

   Enshuai Zhou

   DBLP profile ↗ORCID search ↗
6. Hypothesis, Verification, and Induction: Grounding Large Language Models with Self-Driven Skill Learning
   AAAI 2024 ·

   Shaohui Peng

   DBLP profile ↗ORCID search ↗
7. OCEAN-MBRL: Offline Conservative Exploration for Model-Based Offline Reinforcement Learning
   AAAI 2024 ·

   Fan Wu

   DBLP profile ↗ORCID search ↗
8. Prompt-based Visual Alignment for Zero-shot Policy Transfer
   ICML 2024 ·

   Haihan Gao

   DBLP profile ↗ORCID search ↗