Preview build on GitHub Pages. The open registry will live at e2er.org.
Skip to content
Demonstrator · items marked Example are invented · what exists today
E2ER

External pipelines · RISE project catalogue

Tongyi DeepResearch

An agentic large language model purpose-built for long-horizon deep-information-seeking tasks (arXiv:2510.24701), shipped both as open weights (30.5B total / 3.3B active) and as inference code with ReAct and 'Heavy' (IterResearch) modes. Sits in the literature/ synthesis block of the RISE diagram, with state-of-the-art reported results on agentic-search benchmarks (BrowseComp, FRAMES, Humanity's Last Exam).

Indexed in RISE · activeConformance with the standard plannedProject site

What it does

Treats agentic-research capability as a *model-training* problem, not just an orchestration problem: continual agentic pre-training, fully automated synthetic data generation, and end-to-end on-policy RL with GRPO. Distinguishes itself from prompt-engineering pipelines by shipping a model purpose-trained for research-style tool use.

Focus
literature
Inputs
research-question
Outputs
cited-response, research-report
Architecture
tool-use, rag-knowledge-base, iterative-loop
Maintained by
Tongyi Lab, Alibaba
Started
2025

Description

Data model
Discipline
General
Method family
Literature review
Design
not specified
Research stage
Research questionLiterature discoveryLiterature synthesis
Contributors
Tongyi Lab, Alibaba
Usage
not used in published research yet
Source
RISE project catalogue · projects/landscape · @4c17bae
Record
pipeline:tongyi-deepresearch · JSON

Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.

Bring it into the standard

A pipeline built outside E2ER can meet the standard by describing its steps as a template, attaching the floor of checks and publishing evaluation records. Its authors keep ownership and credit.