148 citations · 259 across the 43 of their papers we have counts for
46 papers
SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents
Shuzheng Gao, Wenhao Zeng, Zhaojian Yu +5
Long-horizon software engineering agents often need to manage lengthy and noisy interaction histories under limited context budgets. Existing memory management methods typically re…
Unlocking Proactivity in Task-Oriented Dialogue
Azure Zhang, Ning Gao, Yuqin Dai +7
Proactive task-oriented dialogue (TOD), such as outbound sales, demands a persuasive agent that actively probes the user's concerns and steers the conversation toward acceptance wi…
Dependency-Guided Repository-Level C-to-Rust Translation with Reinforcement Alignment
Jia Feng, Wenjie Gan, Cuiyun Gao +5
Automating C-to-Rust migration is critical for improving software security without sacrificing performance. Traditional rule-based methods struggle with diverse C idioms, often pro…
AgenticDB: Self-Evolving Reconfiguration Framework for Database Workloads
Xinyue Yang, Chaozheng Wang, Chen Zheng +2
Configuration tuning is critical to database performance but remains difficult in real deployments. Despite notable advances, prior methods still leave substantial performance pote…
Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning
Hongbin Zhang, Chaozheng Wang, Kehai Chen +4
On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference…
SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades
Man Ho Lam, Chaozheng Wang, Hange Liu +5
Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolution. Existing benchmarks have…
Cascaded Code Editing: Large-Small Model Collaboration for Effective and Efficient Code Editing
Chaozheng Wang, Zezhou Yang, Shuzheng Gao +7
Code editing constitutes a fundamental practice in software development, wherein developers modify existing codebases according to natural language requirements. Accurate code edit…
On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation
Jia Feng, Zhanyue Qin, Cuiyun Gao +4
Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be o…
SAGE: A Service Agent Graph-guided Evaluation Benchmark
Ling Shi, Yuqin Dai, Ziyin Wang +7
The development of Large Language Models (LLMs) has catalyzed automation in customer service, yet benchmarking their performance remains challenging. Existing benchmarks predominan…
WARBENCH: A Comprehensive Benchmark for Evaluating LLMs in Military Decision-Making
Zongjie Li, Chaozheng Wang, Yuchong Xie +2
Large Language Models are increasingly being considered for deployment in safety-critical military applications. However, current benchmarks suffer from structural blindspots that…
Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue
Ning Gao, Wei Zhang, Yuqin Dai +6
The rapid evolution of Large Language Models (LLMs) has accelerated the transition from conversational chatbots to general agents. However, effectively balancing empathetic communi…
SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue
Yuqin Dai, Ning Gao, Wei Zhang +6
Large Language Models have demonstrated remarkable capabilities in open-domain dialogues. However, current methods exhibit suboptimal performance in service dialogues, as they rely…
Automated Prompt Generation for Code Intelligence: An Empirical study and Experience in WeChat
Kexing Ji, Shiyun Fu, Cuiyun Gao +4
Large Code Models (LCMs) show potential in code intelligence, but their effectiveness is greatly influenced by prompt quality. Current prompt design is mostly manual, which is time…
TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework
Shuzheng Gao, Eric John Li, Man Ho Lam +5
Large foundation models are fundamentally transforming the software engineering landscape, demonstrating exceptional capabilities across diverse tasks such as code generation, debu…
SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning
Shuzheng Gao, Chaozheng Wang, Cuiyun Gao +1
Code generation, the task of creating executable programs from natural language requirements, has recently seen tremendous advances through Chain-of-Thought (CoT) reasoning, which…
REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration
Yisu Wang, Ming Wang, Haoyuan Song +4
Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently ar…
JSProtect: A Scalable Obfuscation Framework for Mini-Games in WeChat
Zhihao Li, Chaozheng Wang, Zongjie Li +12
The WeChat mini-game ecosystem faces rampant intellectual property theft to other platforms via secondary development, yet existing JavaScript obfuscation tools are ill-equipped fo…
JSidentify-V2: Leveraging Dynamic Memory Fingerprinting for Mini-Game Plagiarism Detection
Zhihao Li, Chaozheng Wang, Zongjie Li +9
The explosive growth of mini-game platforms has led to widespread code plagiarism, where malicious users access popular games' source code and republish them with modifications. Wh…
A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat
Zezhou Yang, Ting Peng, Cuiyun Gao +3
Code completion, a crucial task in software engineering that enhances developer productivity, has seen substantial improvements with the rapid advancement of large language models…
RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry
Chaozheng Wang, Zezhou Yang, Shuzheng Gao +5
Code completion, a crucial practice in industrial settings, helps developers improve programming efficiency by automatically suggesting code snippets during development. With the e…
UMoE: Unifying Attention and FFN with Shared Experts
Yuanhang Yang, Chaozheng Wang, Jing Li
Sparse Mixture of Experts (MoE) architectures have emerged as a promising approach for scaling Transformer models. While initial works primarily incorporated MoE into feed-forward…
CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
Man Ho Lam, Chaozheng Wang, Jen-tse Huang +1
Large Language Models (LLMs) have recently demonstrated strong capabilities in code-related tasks, but their robustness in code reasoning under perturbations remains underexplored.…
IDInit: A Universal and Stable Initialization Method for Neural Network Training
Yu Pan, Chaozheng Wang, Zekai Wu +3
Deep neural networks have achieved remarkable accomplishments in practice. The success of these networks hinges on effective initialization methods, which are vital for ensuring st…
The Prompt Alchemist: Automated LLM-Tailored Prompt Optimization for Test Case Generation
Shuzheng Gao, Chaozheng Wang, Cuiyun Gao +4
Test cases are essential for validating the reliability and quality of software applications. Recent studies have demonstrated the capability of Large Language Models (LLMs) to gen…