@tom_doerr: Open-source agent for long-horizon deep research https://github.com/TIGER-AI-Lab/OpenResearcher…
Summary
TIGER-AI-Lab releases OpenResearcher, an open-source agent designed to automate long-horizon deep research tasks.
Similar Articles
@tom_doerr: Generates 96,000 high-quality deep research trajectories and provides a fully open-source recipe for training agentic l…
OpenResearcher is an open-source project from TIGER-AI-Lab that provides 96,000 deep research trajectories and a recipe to train agentic language models for long-horizon web research without external APIs. It includes a dataset, model, and demo, and has been adopted by NVIDIA's Nemotron models.
@trendtech33566: 【Breaking News】An OSS that fully reproduces the Deep Research workflow in an open manner has appeared: OpenResearcher, …
OpenResearcher is an open-source project that fully reproduces the Deep Research workflow, providing datasets, models, and demos. It enables researchers and AI agent developers to build, train, and evaluate deep research pipelines in an open manner.
@tom_doerr: Automates research workflows with persistent multi-agent memory https://github.com/EvoScientist/EvoScientist…
EvoScientist is an open-source framework that automates research workflows using self-evolving AI scientists with persistent multi-agent memory, adopting a human-on-the-loop paradigm for autonomous research exploration and insight generation.
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
OpenResearcher presents a reproducible pipeline for training deep research agents using offline search environments and synthesized trajectories, achieving significant accuracy improvements on benchmark tasks like BrowseComp-Plus.
@tom_doerr: AI agents for data analysis, plugins, and web browsing https://github.com/xlang-ai/OpenAgents…
OpenAgents is an open platform for using and hosting language agents in everyday life, featuring agents for data analysis, plugins, and web browsing, with open code and a demo.