Xkev
/

deepresearch_single

image-text-to-text

Model card Files Files and versions

gemma-4-E2B-it — Deep Research Single-Agent RL

Paper: Learning Self-Orchestration in Decentralized Agent Swarms

Code: https://github.com/Embodied-Minds-Lab/MPT

For the three-agent counterpart, see Xkev/deepresearch_society.

Training

Initialization: single-agent SFT cold start of google/gemma-4-E2B-it
Dataset: OpenResearcher deep-research tasks
Framework: verl
Algorithm: monolithic REINFORCE
Hyperparameters: lr=1e-6, lr_warmup_ratio=0, constant schedule

Intended use

Research on multi-agent post-training and deep research agents. Not intended for general dialog or production.

License

Apache-2.0.

Downloads last month: 13

Safetensors

Model size

6B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Xkev/deepresearch_single

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Finetuned

(403)

this model

Paper for Xkev/deepresearch_single

Learning Self-Orchestration in Decentralized Agent Swarms

Paper • 2610.22322 • Published 3 days ago • 11