Dataset Card
SWE-Misbehavior is a benchmark for measuring boundary violations made by software coding agents, meaning actions that go beyond what the user asked for. Examples include rewriting code around the target function, changing signatures, touching unrelated files, deleting the wrong files, running unrequested commands, or skipping files the agent needed to read. The benchmark has 7,427 task instances across 3 task families and 9 subsets. All of them are built on real-world Python repositories from DevEval (10 domains: Communications, Database, Internet, Multimedia, Scientific-Engineering, Security, Software-Development, System, Text-Processing, Utilities). Each instance comes with 50 paraphrased…
Excerpt from the card by Nguyen Duc Anh.
Structure
cg_lv1 1,253 rows
instance_idstringnamespacestringcompletion_pathstringnew_completion_pathstringproject_pathstringfunction_namestringpromptlistneed_readlist
cg_lv2 1,253 rows
instance_idstringnamespacestringcompletion_pathstringnew_completion_pathstringproject_pathstringfunction_namestringpromptlistneed_readlist
cg_lv3 570 rows
instance_idstringnamespacestringcompletion_pathstringnew_completion_pathstringproject_pathstringfunction_namestringpromptlistneed_readlist
exec_execute 570 rows
instance_idstringnamespacestringcompletion_pathstringproject_pathstringfunction_namestringpromptlistneed_readlist
exec_testing 570 rows
instance_idstringnamespacestringcompletion_pathstringproject_pathstringfunction_namestringpromptlistneed_readlist
fm_aef 257 rows
instance_idstringnamespacestringcompletion_pathstringfunction_namestringpromptlistneed_updatelist
fm_anf 904 rows
instance_idstringnamespacestringcompletion_pathstringfunction_namestringpromptlistneed_updatelist
fm_delf 1,000 rows
instance_idstringcompletion_pathstringpromptlist
fm_delif 1,050 rows
instance_idstringcompletion_pathstringpromptlistdmlisttaken_fromlistneed_readlist