Qingshui Gu — accepted AI-conference papers

2026

NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents

Jingzhe Ding, Shengda Long, Changxin Pu, Ge Zhang, zhou huan, Hongwan Gao +44

ICML 2026poster

Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks primarily evaluate short-horizon behaviors such as localized code generation, scaffolded completion, or repository repair, leaving it unclear whether agents can sustain coherent re…

Cited by 0 Source ↗Scholar ↗

2026

TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling

Yizhi Li, Qingshui Gu, Zhoufutu Wen, Ziniu Li, Ruibin Yuan, Tianshun Xing +13

ICML 2026poster

Recent advancements in aligning large language models via reinforcement learning have achieved remarkable gains in solving complex reasoning problems, but at the cost of expensive on-policy rollouts and limited exploration of diverse reasoning paths. In this work, we introduce TreePO, involving a se…

Cited by 0 Source ↗Scholar ↗