Author

Qingwei Lin

Observed name: Lin, Qingwei

Observed institution: Microsoft (United States)

OpenAlex ID: A5079356390

WebXSkill: Skill Learning for Autonomous Web Agents

2026 · Zhaoyang Wang, Qianhui Wu, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 26

PDF

AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces

2026 · Park, Sungho, Kim, Wonjoong, et al. · arXiv (Cornell University) · 20

PDF

Computer-Using World Model

2026 · Guan, Yiming, Yu, Rui, et al. · arXiv (Cornell University) · 16

PDF

RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms

2026 · Li, Kenan, Li, Rongzhi, et al. · arXiv (Cornell University) · 12

PDF

Triangle: Empowering Incident Triage with Multi-Agent

2025 · Zhaoyang Yu, Aoyang Fang, et al. · IEEE/ACM International Conference on Automated Software Engineering (ASE) · 11

Beyond State Consistency: Behavior Consistency in Text-Based World Models

2026 · Youling Huang, Guanqiao Chen, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 6

PDF

Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments

2026 · Qi, Haomin, Wang, Xingliang, et al. · arXiv (Cornell University) · 3

PDF

Update from Hell: Can Coding Agents Survive Hidden Breakage in Dependency Upgrades?

2026 · Luo, Zijian, He, Runzhi, et al. · arXiv (Cornell University) · 2

PDF

Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks

2026 · Rongyuan Tan, Jue Zhang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2

PDF

A Benchmark for Language Models in Real-World System Building

2026 · Jin, Weilin, Zhao, Chenyu, et al. · arXiv (Cornell University) · 1

PDF

TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search

2026 · Shi, Zhuofan, Ma, Mingzhe, et al. · arXiv (Cornell University)

PDF

RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository

2026 · Association for Computational Linguistics 2026, Chen, Xu, et al. · Underline Science Inc.

Gradient-Guided Multi-Judge Prompt Optimization

2026 · Association for Computational Linguistics 2026, Huang, Yue, et al. · Underline Science Inc.

LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals

2026 · Association for Computational Linguistics 2026, Dong, Hang, et al. · Underline Science Inc.

CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents

2026 · Association for Computational Linguistics 2026, Fu, Wenjie, et al. · Underline Science Inc.

Revisiting Auxiliary Losses for Conditional Depth Routing: An Empirical Study

2026 · Lin, Qingwei · arXiv (Cornell University)

PDF

DUET: Joint Exploration of User Item Profiles in Recommendation System

2026 · Chen, Yue, Sun, Yifei, et al. · arXiv (Cornell University)

PDF

Prediction-Guided Design for Software Systems

2020 · Si Qin, Qingwei Lin · National Conference on Artificial Intelligence

Works count: 18

Citation count: 99

H-index: 6

I10-index: 5