e2rea1

RouteWeaver-4B

README

License: apache-2.0

What this model does

It is not a chat model and it does not answer questions. It writes routing actions, and the surrounding agent loop executes them against a worker pool:

text

<mode>agentic</mode><route model="worker_3" role="planner" refs="">Split the problem into sub-tasks: ...</route><observation id="n1" role="planner">...</observation><route model="worker_3" role="executor" refs="n1">Compute ...</route><observation id="n2" role="executor">...</observation><answer>9</answer>

Three modes share one action grammar:

Table with columns: mode, execution
mode	execution
`single`	exactly one worker call
`multi`	two to four sequential calls, each seeing the previous observation
`agentic`	up to eight calls over role-structured layers (planner / executor / verifier / summarizer) with explicit references between them

Workers are addressed only by anonymous ids (worker_1 … worker_6) that the prompt pairs with capability descriptions; the router never sees model names or prices. The ids are positional: they mean what the prompt says they mean, so the model must be served with the same pool definition it was trained with (configs/route_channels.yaml in the code repository).

Usage

The model only behaves as a router inside the agent loop that parses its actions and calls the workers. Use the code repository:

bash

git clone https://github.com/LaughKing/RouteWeaver && cd RouteWeaverbash setup_env.sh && conda activate routeweaver CKPT=$(python -c "from huggingface_hub import snapshot_download as d; print(d('e2rea1/RouteWeaver-4B'))")TAG=routeweaver GPU=0 bash scripts/eval.sh paper

Loading the weights on their own works as usual, and is useful for inspecting what it emits:

python

from transformers import AutoModelForCausalLM, AutoTokenizermodel = AutoModelForCausalLM.from_pretrained("e2rea1/RouteWeaver-4B", dtype="bfloat16")tok = AutoTokenizer.from_pretrained("e2rea1/RouteWeaver-4B")

This model is trained with α = 0 — task reward only. Three cost-aware operating points of the same method are in RouteWeaver-4B-cost: α = 0.1 cuts worker cost 23% for 1.0 point of accuracy, α = 0.3 cuts it 61% for 3.1 points.

Decoding used for every reported number: greedy at evaluation time (temperature 0.8 / top-p 0.95 during training), prompts capped at 6,144 tokens, the multi-turn response budget at 16,384, each observation at 2,048.

Worker pool

The six frozen workers the router was trained against. Serving a different pool changes what the ids mean, and the policy's choices stop being meaningful.

Table with columns: id, model
id	model
worker_1	Qwen3-8B
worker_2	Llama-3.1-8B-Instruct
worker_3	Qwen3-30B-A3B-Instruct-2507
worker_4	Gemma-3-27B-IT
worker_5	Llama-3.3-70B-Instruct
worker_6	Gemini-2.5-Flash-Lite

Limitations

Pool-specific. The policy learned which anonymous id is good at what. It does not transfer to a different worker pool without retraining.
Not a standalone model. Without the agent loop it emits actions nobody executes.
It inherits the limitations of the workers it calls: a wrong worker answer propagates, and the router cannot verify facts itself.
Trained on Math / Code / Knowledge / Reason / Recall questions in English.

Citation

bibtex

@article{routeweaver2026,  title   = {RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing},  author  = {Wang, Xiaohan and Zhang, Haozhen and Liu, Qingyuan and Feng, Tao and Wang, Wenya},  journal = {arXiv preprint},  year    = {2026}}

Built on verl and vLLM; the base model is Qwen3-4B-Instruct-2507.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

e2rea1

Model Tree

Base

Qwen/Qwen3-4B-Instruct-2507

Fine-tuned

this model

Input Modalities

Text

Output Modalities