PPO-LLM adaptively selects among eight prompting techniques using an 11-dimensional state vector to guide an LLM toward higher branch and line coverage than static baselines on 20 benchmark programs.
Automated control logic test case generation using large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PPO guided Agentic Pipeline for Adaptive Prompt Selection and Test Case Generation
PPO-LLM adaptively selects among eight prompting techniques using an 11-dimensional state vector to guide an LLM toward higher branch and line coverage than static baselines on 20 benchmark programs.