conftrace_
← Authors

Runqing Miao

1 papers · 2026–2026 · 1 conference · across top CS/AI conferences

Conferences

ACL (1)

Top co-authors

Jing Huo (1) Jiaheng Liu (1) Fanyu Meng (1) Tianpei Yang (1) Yang Gao (1) Yuyao Zhang (1) Junlan Feng (1) Siyuan Gan (1) Boyan Wang (1) Linjian Meng (1)

Keywords

reinforcement learning (1) reward hacking (1) large reasoning model (1)

Papers

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning ACL 2026