OpenHands: Open Platform for AI Software Agents and What It Means for Finance Automation
OpenHands' CodeAct agent scores 26% on SWE-Bench Lite, showing what AI agents reliably do today. Finance automation should start tightly scoped, not autonomous.
#open-source
Отворен код
Инструменти с отворен код, рамки и изследователски артефакти за финансов ИИ
WebArena: The 812-Task Benchmark That Measures What Web Agents Actually Can and Cannot Do
GPT-4 finishes just 14.41% of WebArena's 812 web tasks versus 78.24% for humans; agents mostly fail by falsely declaring a task impossible.
TableLlama: Can a 7B Open Model Match GPT-4 on Table Understanding?
TableLlama beats GPT-4 on column type annotation (F1 94 vs 32) but trails by 33 points on WikiTQ compositional reasoning.
SWE-agent: How Interface Design Unlocks Automated Software Engineering
SWE-agent's Agent-Computer Interfaces lifted GPT-4 Turbo from raw shell to 12.47% on SWE-bench, a 10.7-point gain from interface design alone.