← all releases
Salesforce AI Research·Feb 10, 2026·Not specified·open source

Wide and Deep Research Agent (W&D)

The Wide and Deep (W&D) research agent is a framework developed by Salesforce AI Research to enhance the efficiency of deep research agents by incorporating parallel tool calling. This approach allows agents to perform multiple tool calls simultaneously within a single reasoning step, significantly improving performance on deep research benchmarks while reducing the number of turns required to obtain correct answers.

Agentic AIAI AgentsLLMs
visit website
overview

The Wide and Deep (W&D) research agent is a framework developed by Salesforce AI Research to enhance the efficiency of deep research agents by incorporating parallel tool calling. This approach allows agents to perform multiple tool calls simultaneously within a single reasoning step, significantly improving performance on deep research benchmarks while reducing the number of turns required to obtain correct answers.

key features
  • 01Parallel tool calling within a single reasoning step
  • 02Improved performance on deep research benchmarks
  • 03Reduction in the number of turns to obtain correct answers
  • 04Enhanced efficiency in deep research tasks
related productsbrowse all →
llmockopen sourcellmock is a deterministic mock LLM server designed for testing purposes. It provides a real HTTP server with authentic SSE streams, allowing developers to simulate interactions with various LLM APIs like OpenAI, Claude, and Gemini without incurring costs or dealing with non-deterministic results.AIBuildAIopen sourceAIBuildAI is an AI agent that autonomously constructs AI models. Given a specific task, it initiates an agent loop to analyze the problem, design models, and execute training processes, all without human intervention.MiroThinkeropen sourceMiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.