29 citations · 49 across the 18 of their papers we have counts for
20 papers
MatToolBench: Benchmarking Multimodal Agents in Real-World Materials Science Workflows
Mei Wu, Rui Xie, Runyu Zhang +6
Multimodal GUI agents have achieved impressive results on general software benchmarks, yet their ability to operate professional scientific software remains largely unexplored. In…
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
Shuai Bai, Jiayong Deng, Sicheng Fan +30
Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Real digital work requires both…
Complex Problem Solving in Large Language Models: A Statistical Control Survey and Diagnostic Framework
Jiazhang Cai, Tao Wang, Ruidong Zhang +35
Complex problem solving (CPS) with large language models (LLMs) is often framed as a matter of stronger reasoning or longer generation. Yet early-step error amplification, prompt b…
AttnCompress: Dynamic Attention-Guided Trajectory Compression for Software Engineering Agents
Zhengran Zeng, Yixin Li, Rui Xie +2
The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE tasks. However, the trial-and-error…
Qwen-CUA: Native Computer Use for (almost) Everything
Dunjie Lu, Shuai Bai, Tianyi Bai +42
Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive expe…
MoodBench 1.0: An Evaluation Benchmark for Emotional Companionship Dialogue Systems
Haifeng Jing, Yujie Hou, Junfei Liu +4
With the rapid development of Large Language Models, dialogue systems are shifting from information tools to emotional companions, heralding the era of Emotional Companionship Dial…
Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigation
Bo Li, Zhenghua Xu, Rui Xie
Multilingual Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to perform knowledge-intensive tasks in multilingual settings by leveraging retrieved documen…
Benchmarking and Studying the LLM-based Agent System in End-to-End Software Development
Zhengran Zeng, Yixin Li, Rui Xie +2
The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluati…
SWR-Bench: Assessing LLM Performance in Real-World Code Review Comment Generation
Zhengran Zeng, Ruikai Shi, Keke Han +7
Automated Code Review (ACR) is crucial for software quality, yet existing benchmarks often fail to reflect real-world complexities, hindering the evaluation of modern Large Languag…
Seed&Steer: Guiding Large Language Models with Compilable Prefix and Branch Signals for Unit Test Generation
Shuaiyu Zhou, Zhengran Zeng, Xiaoling Zhou +3
Unit tests play a vital role in the software development lifecycle. Recent advances in Large Language Model (LLM)-based approaches have significantly improved automated test genera…
Mitigating Spurious Correlations with Causal Logit Perturbation
Xiaoling Zhou, Wei Ye, Rui Xie +1
Deep learning has seen widespread success in various domains such as science, industry, and society. However, it is acknowledged that certain approaches suffer from non-robustness,…
TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents
Bofei Zhang, Zirui Shang, Zhi Gao +7
Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks. Ho…
Enhancing In-Context Learning via Implicit Demonstration Augmentation
Xiaoling Zhou, Wei Ye, Yidong Wang +4
The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential…
Boosting Model Resilience via Implicit Adversarial Data Augmentation
Xiaoling Zhou, Wei Ye, Zhemg Lee +2
Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially t…
CoderUJB: An Executable and Unified Java Benchmark for Practical Programming Scenarios
Zhengran Zeng, Yidong Wang, Rui Xie +2
In the evolving landscape of large language models (LLMs) tailored for software engineering, the need for benchmarks that accurately reflect real-world development scenarios is par…
CodeShell Technical Report
Rui Xie, Zhengran Zeng, Zhuohao Yu +3
Code large language models mark a pivotal breakthrough in artificial intelligence. They are specifically crafted to understand and generate programming languages, significantly boo…
MindRef: Mimicking Human Memory for Hierarchical Reference Retrieval with Fine-Grained Location Awareness
Ye Wang, Xinrun Xu, Zhiming Ding
When completing knowledge-intensive tasks, humans sometimes need an answer and a corresponding reference passage for auxiliary reading. Previous methods required obtaining pre-segm…
PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
Yidong Wang, Zhuohao Yu, Zhengran Zeng +10
Instruction tuning large language models (LLMs) remains a challenging task, owing to the complexity of hyperparameter selection and the difficulty involved in evaluating the tuned…
Exploiting Pseudo Image Captions for Multimodal Summarization
Chaoya Jiang, Rui Xie, Wei Ye +2
Cross-modal contrastive learning in vision language pretraining (VLP) faces the challenge of (partial) false negatives. In this paper, we study this problem from the perspective of…
Low-Resources Project-Specific Code Summarization
Rui Xie, Tianxiang Hu, Wei Ye +1
Code summarization generates brief natural language descriptions of source code pieces, which can assist developers in understanding code and reduce documentation workload. Recent…