← all releases
StepFun AI·Dec 25, 2025·Not specified·open source

Step-DeepResearch

Step-DeepResearch is a cost-effective, end-to-end deep research agent model designed for autonomous information exploration and professional report generation in open-ended research scenarios. It integrates atomic capabilities such as planning, information seeking, reflection, and report generation to perform comprehensive research tasks. The model is trained using a progressive pipeline that includes agentic mid-training, supervised fine-tuning, and reinforcement learning, enabling it to handle complex research workflows efficiently.

AI AgentsAgentic AI
visit website playground ↗
overview

Step-DeepResearch is a cost-effective, end-to-end deep research agent model designed for autonomous information exploration and professional report generation in open-ended research scenarios. It integrates atomic capabilities such as planning, information seeking, reflection, and report generation to perform comprehensive research tasks. The model is trained using a progressive pipeline that includes agentic mid-training, supervised fine-tuning, and reinforcement learning, enabling it to handle complex research workflows efficiently.

key features
  • 01Atomic Capability Integration
  • 02Progressive Training Pipeline
  • 03Strong Performance Across Model Scales
  • 04Superior Cost-Effectiveness
related productsbrowse all →
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.Letta Code SDKopen sourceThe Letta Code SDK is a software development kit that enables developers to build deeply personalized agents with persistent memory that learn over time. It serves as the interface to Letta Code, facilitating the creation of stateful agents capable of continuous learning and improvement.OB-1open sourceOB-1 is a self-improving coding agent developed by OpenBlock Labs, designed to autonomously handle the full development lifecycle, from project management to pull requests. It integrates seamlessly into existing workflows, enhancing productivity and code quality.