Search Results for "web browser test"

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).

Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.

One-Click to deploy well-designed AutoGPT-Next-Web web UI on Vercel.

TinyCog is a cognitive architecture (perception, action, reasoning, planning, and language) with a focus on representing "self-models" (physical, capabilities, intentions, social, historical, "cognitive stream") in order to implement social reasoning and collaborative planning in a "hunter domain" test bed. We use Prolog, RDF Triples, Description Logic and a HTN-Planner as base technologies.