Predicting Program Exit Code with LLMs and Programming Language Semantics
cs.PL, cs.AI, cs.CL, cs.SE
Submitted: 2026-09-01
Updated: 2026-09-01
Code: https://github.com/EngineeringSoftware/prex
Terminology
Sources
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- Learned or Memorized ? Quantifying Memorization Advantage in Code LLMs
- CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
- LongCoder: A Long-Range Pre-trained Language Model for Code Completion
- Qwen2.5-Coder Technical Report
- Ministral 3
- MarsCode Agent: AI-native Automated Bug Fixing
- Large Language Models as Code Executors: An Exploratory Study
- Code Simulation Challenges for Large Language Models
- Detecting Functional Memorization in Code Language Models
- NExT: Teaching Large Language Models to Reason about Code Execution
- CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
- LLMs versus the Halting Problem: Characterizing Program Termination Reasoning
- LLMs Lean on Priors, Not Programming Language Semantics