8 papers
Lossless Tensor Compression as Program Synthesis
Jieke Shi, Junda He, Wenjia Jiang +11
Model checkpoints are growing in both number and size, which makes archival, transfer, and deployment increasingly costly. General-purpose compressors can reduce storage requiremen…
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…
Compiling Code LLMs into Lightweight Executables
Jieke Shi, Junda He, Zhou Yang +6
The demand for better prediction accuracy and higher execution performance in neural networks continues to grow. The emergence and success of Large Language Models (LLMs) have prod…
Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls
Zeyu Zhang, Guohao Li, Zhenchang Xing +3
The ability to use tools is fundamental for large language model (LLM) agents. Given a task, existing systems use LLMs to plan and generate tool calls, which are executed by real-w…
CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction
Jun Gao, Yun Peng, Qian Qiao +6
Despite strong performance on code generation tasks, it remains unclear whether large language models (LLMs) genuinely reason about code execution. Existing code reasoning benchmar…
Environment-Aware Code Generation: How far are We?
Tongtong Wu, Rongyi Chen, Wenjie Du +6
Recent progress in large language models (LLMs) has improved code generation, but most evaluations still test isolated, small-scale code (e.g., a single function) under default or…