FeedbackLLM uses line and branch coverage feedback agents in an iterative multi-agent process with a redundancy cache to generate test cases achieving higher coverage than baselines on standard C and Python benchmarks while scaling linearly in time.
Chatunitest: A framework for llm-based test generation
3 Pith papers cite this work. Polarity classification is still indexing.
fields
cs.SE 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
LLMs produce counterexamples that remove up to 11.68% of invalid assertions from dynamic inference and raise precision by up to 7% on benchmarks without hurting recall.
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.
citing papers explorer
-
FeedbackLLM: Metadata driven Multi-Agentic Language Agnostic Test Case Generator with Evolving prompt and Coverage Feedback
FeedbackLLM uses line and branch coverage feedback agents in an iterative multi-agent process with a redundancy cache to generate test cases achieving higher coverage than baselines on standard C and Python benchmarks while scaling linearly in time.
-
Improving Dynamic Specification Inference with LLM-Generated Counterexamples
LLMs produce counterexamples that remove up to 11.68% of invalid assertions from dynamic inference and raise precision by up to 7% on benchmarks without hurting recall.
-
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.