ML
Michael R. Lyu
cs.SEcs.CLcs.AIcs.LGcs.CVAlgorithmscs.CRArtificial Intelligencecs.DCcs.MM
On Valency
published · living versionsW_d3zq9krp·v1 · currentpublished
Training LLM Agents to Automate LLM Post-Training with RSI-Dojo
with Shuzheng Gao, Zhaojian Yu, Penghao Yin, Yuling Shi +2
1 version
W_3zr3dbgw·v1published
W_ugycxvp8·v1published
Preprints & journals
260 papers in the corpus · 2002–2026InterWebCoder: Learning Interactive Webpage Generation from Executable Tests via Reinforcement Learning2610.28610v1 · Jingyu Xiao, Dasen Dai, Yuxuan Wan et al.2026 · 0 citationsarXivon Valency
TraceLite: Efficient Trace Reduction for SWE Agents via Optical Compression and Redundancy Removal2610.28612v1 · Jingyu Xiao, Qianxi Liu, Yintong Huo et al.2026 · 0 citationsarXivon Valency
MatLoom: Layered Text-to-Material Generation in a Compact Program Space2609.40322v1 · Anson Y. Lam, Shuqing Li, Michael R. Lyu2026 · 0 citationsarXiv
Frozen Scenes, Shifting Winners: Configuration Fragility in Text-to-3D Evaluation2610.00447v1 · Anson Y. Lam, Shuqing Li, Michael R. Lyu2026 · 0 citationsarXiv
From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause Analysis2608.25661v1 · Haiyu Huang, Jiewei Lyu, Zhihan Jiang et al.2026 · 0 citationsarXiv
VisualRepair: Dynamic Tool Calling and Region Focusing for Visual Software Issue Repair2607.14075v1 · Jingyu Xiao, Zhongyi Zhang, Haoran Hou et al.2026 · 1 citationarXiv
MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models2607.11594v1 · Tsz Hei Fan, Choi Wing Fung, Yuxuan Wan et al.2026 · 0 citationsarXiv
MicroAgent: Context-Augmented Multi-Agent Framework for Automatic Microservice Decomposition2606.29742v2 · Zishan Su, Junjie Huang, Shiwen Shan et al.2026 · 0 citationsarXiv
SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents2606.28434v1 · Shuzheng Gao, Wenhao Zeng, Zhaojian Yu et al.2026 · 0 citationsarXiv
VideoLatent: Video-Language Learning via Latent Self-Forcing2606.22870v1 · Zi-Yuan Hu, Zicong Tang, Shijia Huang et al.2026 · 0 citationsarXiv
Bringing Managed Language Support to WebAssembly with External Library Linking2606.21919v1 · Shuyao Jiang, Ruiying Zeng, Yangfan Zhou et al.2026 · 0 citationsarXiv
From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements2605.17242v2 · Yuxuan Wan, Tingshuo Liang, Jiakai Xu et al.2026 · 0 citationsarXiv
SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades2605.14415v1 · Man Ho Lam, Chaozheng Wang, Hange Liu et al.2026 · 1 citationarXiv
Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair2605.07276v1 · Jia Li, Yuxin Su, Ting Peng et al.2026 · 0 citationsarXiv
VulKey: Automated Vulnerability Repair Guided by Domain-Specific Repair Patterns2605.01769v3 · Jia Li, Zhuangbin Chen, Yuxin Su et al.2026 · 0 citationsarXiv
Cascaded Code Editing: Large-Small Model Collaboration for Effective and Efficient Code Editing2604.19201v1 · Chaozheng Wang, Zezhou Yang, Shuzheng Gao et al.2026 · 0 citationsarXiv
Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective2604.17814v1 · Meifang Chen, Zhe Yang, Huang Nianchen et al.2026 · 0 citationsarXiv
Automated Logging Is Language-Sensitive: A Multilingual Benchmark and Empirical Study of LLMs2604.17529v2 · Renyi Zhong, Yichen Li, Yulun Wu et al.2026 · 0 citationsarXiv
ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair2603.27333v1 · Jia Li, Zeyang Zhuang, Zhuangbin Chen et al.2026 · 0 citationsarXiv
Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems2603.00468v2 · Yilun Wang, Guangba Yu, Haiyu Huang et al.2026 · 1 citationarXiv
EfficientPosterGen: Semantic-aware Efficient Poster Generation via Token Compression and Accurate Violation Detection2603.00155v1 · Wenxin Tang, Jingyu Xiao, Yanpei Gong et al.2026 · 0 citationsarXiv
ComUICoder: Component-based Reusable UI Code Generation for Complex Websites via Semantic Segmentation and Element-wise Feedback2602.19276v1 · Jingyu Xiao, Jiantong Qin, Shuoqi Li et al.2026 · 1 citationarXiv
Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification2601.15808v2 · Yuxuan Wan, Tianqing Fang, Zaitang Li et al.2026 · 1 citationarXiv
Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs2601.13655v1 · Guangba Yu, Zirui Wang, Yujie Huang et al.2026 · 1 citationarXiv
AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems2601.09393v1 · Zirui Wang, Guangba Yu, Michael R.Lyu2026 · 1 citationarXiv
From Laboratory to Real-World Applications: Benchmarking Agentic Code Reasoning at the Repository Level2601.03731v3 · Jia Li, Yuxin Su, Michael R. Lyu2026 · 0 citationsarXiv
AutoLogger: A Multi-Agent Framework for the End-to-End Automated Logging2511.18528v2 · Renyi Zhong, Yintong Huo, Wenwei Gu et al.2025 · 0 citationsarXiv
ComboBench: Can LLMs Manipulate Physical Devices to Play Virtual Reality Games?2510.24706v1 · Shuqing Li, Jiayi Yan, Chenyu Niu et al.2025 · 0 citationsarXiv
BDiff: Block-aware and Accurate Text-based Code Differencing2510.21094v1 · Yao Lu, Wanwei Liu, Tanghaoran Zhang et al.2025 · 0 citationsarXiv
SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning2510.17130v1 · Shuzheng Gao, Chaozheng Wang, Cuiyun Gao et al.2025 · 1 citationarXiv
TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework2510.17163v1 · Shuzheng Gao, Eric John Li, Man Ho Lam et al.2025 · 0 citationsarXiv
When Shared Worlds Break: Demystifying Defects in Multi-User Extended Reality Software Systems2510.01182v1 · Shuqing Li, Chenran Zhang, Binchang Li et al.2025 · 1 citationarXiv
90% Faster, 100% Code-Free: MLLM-Driven Zero-Code 3D Game Development2509.26161v1 · Runxin Yang, Yuxuan Wan, Shuqing Li et al.2025 · 1 citationarXiv
Metamorphic Testing for Audio Content Moderation Software2509.24215v1 · Wenxuan Wang, Yongjiang Wu, Junyuan Zhang et al.2025 · 0 citationsarXiv
Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development2509.25297v2 · Yuxuan Wan, Tingshuo Liang, Jiakai Xu et al.2025 · 0 citationsarXiv
Trace Sampling 2.0: Code Knowledge Enhanced Span-level Sampling for Distributed Tracing2509.13852v1 · Yulun Wu, Guangba Yu, Zhihan Jiang et al.2025 · 0 citationsarXiv
EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation2509.12159v2 · Jingyu Xiao, Zhongyi Zhang, Yuxuan Wan et al.2025 · 1 citationarXiv
Weakly Supervised Vulnerability Localization via Multiple Instance Learning2509.11312v1 · Wenchao Gu, Yupan Chen, Yanlin Wang et al.2025 · 1 citationarXiv
Integrating Rules and Semantics for LLM-Based C-to-Rust Translation2508.06926v1 · Feng Luo, Kexing Ji, Cuiyun Gao et al.2025 · 3 citationsarXiv
SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval2508.00546v1 · Wenchao Gu, Zongyi Lyu, Yanlin Wang et al.2025 · 0 citationsarXiv
3D Software Synthesis Driven by Constraint-Expressive Intermediate Representation2507.18625v3 · Shuqing Li, Anson Y. Lam, Yun Peng et al.2025 · 0 citationsarXiv
Data Compressibility Quantifies LLM Memorization2507.06056v4 · Yizhan Huang, Zhe Yang, Meifang Chen et al.2025 · 0 citationsarXiv
CCISolver: End-to-End Detection and Repair of Method-Level Code-Comment Inconsistency2506.20558v1 · Renyi Zhong, Yintong Huo, Wenwei Gu et al.2025 · 0 citationsarXiv
SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design2506.07964v1 · Wenxin Tang, Jingyu Xiao, Wenxuan Jiang et al.2025 · 7 citationsarXiv
DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation2506.06251v3 · Jingyu Xiao, Ming Wang, Man Ho Lam et al.2025 · 1 citationarXiv
KPIRoot+: An Efficient Integrated Framework for Anomaly Detection and Root Cause Analysis in Large-Scale Cloud Systems2506.04569v1 · Wenwei Gu, Renyi Zhong, Guangba Yu et al.2025 · 3 citationsarXiv
ColorGo: Directed Concolic Execution2505.21130v1 · Jia Li, Jiacheng Shen, Yuxin Su et al.2025 · 0 citationsarXiv
Larger Is Not Always Better: Exploring Small Open-source Language Models in Logging Statement Generation2505.16590v3 · Renyi Zhong, Yichen Li, Guangba Yu et al.2025 · 4 citationsarXiv
RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry2505.15179v1 · Chaozheng Wang, Zezhou Yang, Shuzheng Gao et al.2025 · 10 citationsarXiv
LLMPrism: Black-box Performance Diagnosis for Production LLM Training Platforms2505.00342v1 · Zhihan Jiang, Rui Ren, Guangba Yu et al.2025 · 3 citationsarXiv
Career total: 905 works. 260 are in this corpus.Showing the 50 most recent.
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.