Magic bet that software-engineering agents need unusually long context windows, building LTM models intended to reason over entire repositories and eventually combine long context with pretraining and agentic reinforcement learning.
SWE-agent reframed language models as software-engineering agents that navigate repositories, edit files and run tests through a specially designed agent-computer interface, moving beyond isolated function generation.
SWE-bench changed coding-model evaluation by asking systems to resolve real GitHub issues inside full repositories, making tests, repository context and patch correctness central to measuring progress.