BQ
Bowen Qin
cs.AIcs.CLcs.CVcs.LGcs.DBcs.IRcs.SE
On Valency
published · living versionsW_nemwv4j2·v1 · currentpublished
BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric Environments
with Ge Qu, Jinyang Li, Xiaohan Xu, Xiaolong Li +4
1 version
Preprints & journals
13 papers in the corpus · 2023–2026BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric Environments2610.29426v1 · Ge Qu, Jinyang Li, Xiaohan Xu et al.2026 · 0 citationsarXivon Valency
Agentic Image Generation in the Wild2610.23269v1 · Yifan Li, Bowen Qin, Kun Zhou et al.2026 · 0 citationsarXiv
Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents2610.17827v1 · Haochen Zhao, Minsheng Hao, Zheng Li et al.2026 · 0 citationsarXiv
ORCA: Evaluating LLMs on Data Science Code Translation2609.30749v1 · Xiaolong Li, Jinyang Li, Bowen Qin et al.2026 · 0 citationsarXiv
Diff-SQL: SQL Efficiency Optimization via Patch Generation and Constraint Alignment2610.06857v1 · Shipei Lin, Duomin Zhang, Xiaolong Li et al.2026 · 0 citationsarXiv
LogDx-CI: Benchmarking Log Reduction Tools for LLM Root-Cause Diagnosis2605.28876v1 · Bowen Qin2026 · 0 citationsarXiv
Beyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFT2511.17405v2 · Yesheng Liu, Hao Li, Haiyu Xu et al.2025 · 0 citationsarXiv
FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions2509.17177v3 · Bowen Qin, Chen Yue, Fang Yin et al.2025 · 0 citationsarXiv
FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model Evaluation2506.09081v3 · Zheqi He, Yesheng Liu, Jing-shu Zheng et al.2025 · 1 citationarXiv
The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models2505.22017v2 · Siqi Fan, Bowen Qin, Peng Han et al.2025 · 0 citationsarXiv
Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets2406.08124v2 · Duanyu Feng, Bowen Qin, Chen Huang et al.2024 · 1 citationarXiv
Towards Understanding the Influence of Reward Margin on Preference Model Performance2404.04932v1 · Bowen Qin, Duanyu Feng, Xi Yang2024 · 0 citationsarXiv
FLM-101B: An Open LLM and How to Train It with $100K Budget2309.03852v3 · Xiang Li, Yiqun Yao, Xin Jiang et al.2023 · 2 citationsarXiv
Career total: 20 works. 13 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.