8 papers
World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning
Yucheng Zhou, Wei Tao, Yiwen Guo +1
World models and multimodal large language models (MLLMs) provide complementary capabilities for predicting future outcomes from static visual observations. World models can genera…
DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents
Sirui Hong, Zhijie Liu, Tengfei Li +3
Evaluating LLM-generated interactive software requires execution in addition to static analysis. The key difficulty is that correctness is a graph-level reachable property over lat…
PlayCoder: Making LLM-Generated GUI Code Playable
Zhiyuan Peng, Wei Tao, Xin Yin +3
Large language models (LLMs) have achieved strong results in code generation, but their ability to generate GUI applications, especially games, remains insufficiently studied. Exis…
Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey
Caihua Li, Lianghong Guo, Yanlin Wang +9
Issue resolution, a complex Software Engineering (SWE) task integral to real-world development, has emerged as a compelling challenge for artificial intelligence. The establishment…
C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations
Chengqian Ma, Wei Tao, Yiwen Guo
Spoken Dialogue Models (SDMs) have recently attracted significant attention for their ability to generate voice responses directly to users' spoken queries. Despite their increasin…
OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution
Lianghong Guo, Wei Tao, Runhan Jiang +7
The GitHub issue resolution task aims to resolve issues reported in repositories automatically. With advances in large language models (LLMs), this task has gained increasing atten…