Search Results for "fix"

SWE-agent turns LMs (e.g. GPT-4) into software engineering agents that can resolve issues in real GitHub repositories. On the SWE-bench, the SWE-agent resolves 12.47% of issues, achieving state-of-the-art performance on the full test set. We accomplish our results by designing simple LM-centric commands and feedback formats to make it easier for the LM to browse the repository, and view, edit, and execute code files. We call this an Agent-Computer Interface (ACI).

PUPS/P3 facilitates development of multi-process multi-host computations by providing tools to emulate colonies of homeostatic organisms. It permits persistent computation, homeostatic resource protection, and asychronous interprocess communication.

...The main contribution of ARGO is to enable the use of perception filters for programming robotic agents. Moreover, ARGO allows an agent to decide when to start or to stop perceiving from its sensors, to fix the interval between each perception and to control these filtering behavior in runtime. LATEST VERSION available at: https://github.com/chon-group/argo