8 papers
Reachability Across the NL/PL Boundary: A Taxonomy-Driven Dataflow Model for LLM-Integrated Applications
Zihao Xu, Xiao Cheng, Ruijie Meng +1
LLM API calls have become a standard programming primitive, but they create a program boundary that disrupts traditional dataflow analysis. A runtime value may be inserted into a n…
Rethinking Complexity Metrics for LLM-Integrated Applications: Beyond Source Code
Zihao Xu, Yuekang Li, Gelei Deng +2
LLM-integrated applications blend natural language prompts with program code, and much of their runtime behavior originates in the prompt layer rather than in the code itself. Exis…
TVIR: Building Deep Research Agents Towards Text-Visual Interleaved Report Generation
Xinkai Ma, Zhiqi Bai, Dingling Zhang +21
Deep Research Agents have shown strong capability in multi-step information retrieval, reasoning, and long-form report generation, but existing benchmarks and systems remain predom…
Socrates or Smartypants: Testing Logic Reasoning Capabilities of Large Language Models with Logic Programming-based Test Oracles
Zihao Xu, Junchen Ding, Yiling Lou +3
Large Language Models (LLMs) have achieved significant progress in language understanding and reasoning. Evaluating and analyzing their logical reasoning abilities has therefore be…
"Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas
Junchen Ding, Penghao Jiang, Zihao Xu +4
As large language models (LLMs) increasingly mediate ethically sensitive decisions, understanding their moral reasoning processes becomes imperative. This study presents a comprehe…
STGCN-LSTM for Olympic Medal Prediction: Dynamic Power Modeling and Causal Policy Optimization
Yiquan Wang, Jiaying Wang, Tin-Yeh Huang +2
This paper proposes a novel hybrid model, STGCN-LSTM, to forecast Olympic medal distributions by integrating the spatio-temporal relationships among countries and the long-term dep…