TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks Paper • 2412.14161 • Published 10 days ago • 44
TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks Paper • 2412.14161 • Published 10 days ago • 44
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents Paper • 2407.16741 • Published Jul 23 • 68
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents Paper • 2407.16741 • Published Jul 23 • 68