3 6 Ke·2025-12-12 00:49Core Insights - Google has launched significant updates to its Gemini Deep Research Agent, including new functionalities and an open-source benchmark for evaluating agent performance in complex research tasks [1][3][5]. Group 1: Gemini Deep Research Agent Updates - The Gemini Deep Research Agent is designed for long-term context gathering and optimization of complex tasks, utilizing the Gemini 3 Pro model, which has achieved state-of-the-art (SOTA) performance with a score of 46.4% on Google's new benchmark [3][7]. - The updated agent features enhanced web search capabilities and lower-cost report generation, making it suitable for industries such as financial services and biotechnology [9][10]. - The agent operates through an iterative process, allowing it to ask questions, read results, and identify knowledge gaps for further searches [7][9]. Group 2: DeepSearchQA Benchmark - DeepSearchQA is a new open-source benchmark with 900 manually designed "causal chain" tasks across 17 domains, aimed at assessing the agent's ability to handle complex, multi-step information queries [10][12]. - Unlike traditional fact-based tests, DeepSearchQA evaluates the comprehensiveness of responses and the agent's memory capabilities, enhancing the assessment of research accuracy [11][12]. Group 3: Interactions API - The Interactions API is designed for agent application development, providing a unified interface for managing complex context and interactions with the Gemini model and agents [14][15]. - This API simplifies the development process by allowing developers to connect their custom agents with Google's built-in agents and models through a single RESTful endpoint [14][15]. Group 4: Future Developments - Google plans to enhance the Gemini ecosystem further by introducing features such as native chart generation for visual analysis reports and improved connectivity to custom data sources through the model context protocol (MCP) [16].