News from the AI & ML world
DeeperML - #deepresearch
|
@the-decoder.com
//
The development of AI agents capable of automating tasks and performing research is rapidly advancing, with several entities contributing to this innovative field. Bytedance has recently open-sourced DeerFlow, a modular multi-agent framework designed to enhance complex research workflows. This framework integrates the capabilities of large language models (LLMs) with domain-specific tools, offering a structured and extensible platform for automating sophisticated research tasks such as information retrieval and multimodal content generation. DeerFlow leverages LangChain and LangGraph to enable robust task orchestration and data flow control, facilitating a collaborative human-in-the-loop setting.
Hugging Face has also introduced its own AI agent, the Open Computer Agent, designed to navigate the web and complete tasks on behalf of users. This agent can interact with websites and applications, handling tasks like getting directions or booking tickets. Unlike passive information sources, the Open Computer Agent actively participates by opening browsers, typing in forms, and clicking buttons, mimicking human interaction. As part of Hugging Face's "smolagents" initiative, the Open Computer Agent is open-source, allowing users to tweak and build upon it for specific use cases. Microsoft researchers have been exploring different approaches to AI agent development, comparing API-based agents with GUI-based agents. Their findings suggest that API agents are generally faster and more reliable due to their direct interaction with software through programmable interfaces. GUI agents, on the other hand, offer greater versatility by mimicking human-like interactions, enabling them to control almost any software with a visible interface, even without an API. While API agents excel in efficiency and security, GUI agents are more adaptable to interface changes and provide better transparency, allowing users to visually audit their actions.
Share:
References :
Classification:
Alexey Shabanov@TestingCatalog
//
OpenAI is now providing access to its Deep Research tool to all ChatGPT users, including those with free accounts. The company is introducing a "lightweight" version of Deep Research, powered by the o4-mini model, designed to be nearly as intelligent as the original while significantly cheaper to serve. This move aims to democratize access to sophisticated AI reasoning capabilities, allowing a broader audience to benefit from the tool's in-depth analytical capabilities.
The Deep Research feature offers users detailed insights on various topics, from consumer decision-making to educational guidance. The lightweight version available to free users enables in-depth, topic-specific breakdowns without requiring a premium subscription. This expansion means free ChatGPT users will have access to Deep Research, albeit with a limitation of five tasks per month. The tool allows ChatGPT to autonomously browse the web, read, synthesize, and output structured reports, similar to tasks conducted by policy analysts and researchers. Existing ChatGPT Plus, Team, and Pro users will also see changes. While still having access to the more advanced version of Deep Research, they will now switch to the lightweight version after reaching their initial usage limits. This approach effectively increases monthly usage for paid users by offering additional tasks via the o4-mini-powered tool. The lightweight version preserves core functionalities like multi-step reasoning, real-time browsing, and document parsing, though responses may be slightly shorter while retaining citations and structured logic.
Share:
References :
Classification:
|
BenchmarksBlogsResearch Tools |