SearchSYS
ToolFirst seen 8/4/2026
Last seen 8/12/2026
Evidence 44 chunks
NEIGHBORHOOD
No graph connections found for this entity yet. It may appear in future ingestion runs.
explore full graph →RELATIONSHIPS
50 connectionsSearchSYS is used to test and evaluate the gem5 simulator.
SearchSYS implements differential testing by running outputs on real hardware and simulator.
TinyLlama is one of the LLMs used by SearchSYS for seed generation.
SearchSYS uses C program generation via LLMs to create initial seed inputs.
SearchSYS uses AFL++ as its fuzzing engine.
Magicoder is one of the LLMs used by SearchSYS for seed generation.
SearchSYS uses CodeBooga as one of its LLMs for test seed generation.
SearchSYS uses Llama2 as one of its LLMs for test seed generation.
SearchSYS uses Phi2 as one of its LLMs for test seed generation.
SearchSYS uses Ollama as the infrastructure for running local LLMs.
The paper presents and discusses SearchSYS as its primary contribution.
SearchSYS supports regression testing by providing test cases tied to specific features of the ARM ISA.
SearchSYS implements fuzzing as one of its testing strategies.
SearchSYS uses GPT-3.5-turbo as one of its LLMs for test seed generation.
SearchSYS uses LLMs to generate initial seeds for the fuzzing process.
SearchSYS uses compiler optimization tokens in its prompt templates to diversify LLM-generated test programs.
SearchSYS applies bit-flip mutations only to a program's compiled binary file.
SearchSYS applies mutation-based testing via custom mutation operators on binaries and their arguments.
SearchSYS employs coverage-guided fuzzing via AFL++ to explore simulator code.
SearchSYS uses prompt engineering with token-filled templates to guide LLM test generation.
SearchSYS applies binary mutation as one of its core mutation operators.
SearchSYS is applied to evaluate gem5's simulation of the ARM Instruction Set Architecture.
SearchSYS results on ARM ISA are compared with its previous results on X86 ISA.
ChatFuzz is compared with SearchSYS in related work as a similar LLM-based fuzzing approach.
SearchSYS uses custom mutator libraries with AFL++.
SearchSYS uses LLM-generated C programs as seed corpora for fuzzing.
cm-gem5c.so is part of the SearchSYS custom mutator components.
SearchSYS creates test cases with parameterized inputs where LLMs provide types for input parameters.
SearchSYS uses prompt engineering to query LLMs for test program generation.
SearchSYS uses zero-shot prompting to query LLMs for test program generation.
SearchSYS uses LLMs to create an initial set of test seeds as C source code.
SearchSYS uses AFL++-based coverage-guided fuzz testing as one of its main components.
SearchSYS is classified as a search-based software testing framework.
SearchSYS applies three mutation operators for testing system simulators.
SearchSYS leverages large language models for initial seed C code generation.
SearchSYS is applied to test gem5's simulation of the ARM Instruction Set Architecture.
SearchSYS is used to evaluate gem5's ARMv8 simulation capabilities.
SearchSYS mentions potential applicability to RISC-V architectures.
SearchSYS was previously used to find bugs in gem5's X86 architecture simulation.
Karine Even-Mendoza is one of the authors of SearchSYS.
SearchSYS uses afl-cmin for test suite minimization before fuzzing.
SearchSYS uses afl-cmin for test suite minimization before fuzzing campaigns.
SearchSYS generates test suites using LLMs and fuzzing.
SearchSYS uses CodeLlama as one of the LLMs for test seed generation.
Bobby R. Bruce is one of the authors of SearchSYS.
Justyna Petke is one of the authors of SearchSYS.
cm-gem5c-types.so is part of the SearchSYS custom mutator components.
Aidan Dakhama is one of the authors of SearchSYS.
SearchSYS uses four C token categories to fill gaps in the template prompts for LLMs.
cm-gem5c-bin.so is part of the SearchSYS custom mutator components.