AI Briefing#llm-agent
The latest AI and developer news about #llm-agent, with the original source and a short summary.
The latest AI and developer news about #llm-agent, with the original source and a short summary.
The OSWorld-v2 average score rose from 45.3 to 64.9 points through harness changes alone, without model training.
With LLM weights frozen, it achieved 87.88% on the GAIA validation set by leveraging a case bank.
RedThread, an open-source CLI for reproducing red team cases of LLM agents and analyzing safety decision factors, has been released.
Alibaba has open-sourced 'Open Code Review', an AI code review tool based on a hybrid architecture that was internally validated for two years.