ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents 事件

ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents arXiv:2604.07789v2 Announce Type: replace-cross Abstract: Recent advances in language model (LM) agents have significantly improved automated software engineering (SWE). Prior work has proposed various agentic workflows and training strategies as well as analyzed failure modes of agentic systems on SWE tasks, focusing on several contextual information signals: Reproduction Test, Regression Test, Edit Location,