Built by Forward AI Labs

We are an AI company that provides recruitment agents. | mira.day

---

MRE-T1: Mira Recruitment Embedding — Thought v1

MRE-T1 (Mira Recruitment Embedding, Thought v1) is the first generation of our reasoning-intensive retrieval model series. The "Thought" in T1 reflects the model's core capability — it thinks before it retrieves, generating explicit reasoning chains to deeply understand query intent before producing embeddings.

MRE-T1 achieves state-of-the-art single-model performance on the BRIGHT benchmark, which evaluates retrieval models on tasks requiring complex reasoning capabilities.

Highlights

• BRIGHT Short nDCG@10: 39.6 — achieves the best single-model result on the short document retrieval leaderboard
• BRIGHT Long nDCG@10: 35.1 — achieves the best single-model result on the long document retrieval leaderboard
• Efficient: Based on Qwen3-4B architecture, significantly smaller than many competing 7-8B models
• Reasoning-aware: Uses task-specific reasoning prompts with a special <emb_token> for embedding extraction

Model Details

Property	Value
Architecture	Qwen3ForCausalLM
Parameters	~4B
Hidden Size	2560
Layers	36
Attention Heads	32 (KV heads: 8)
Max Position	262,144
Precision	bfloat16
Vocabulary	151,670

BRIGHT Benchmark Results

Short Document Retrieval (nDCG@10)

Task	MRE-T1
Biology	55.3
Earth Science	56.5
Economics	32.9
Psychology	48.2
Robotics	33.1
StackOverflow	34.2
Sustainable Living	37.3
LeetCode	35.0
Pony	35.5
AOPS	16.7
TheoremQA (Questions)	43.3
TheoremQA (Theorems)	46.9
Average	39.6

Long Document Retrieval (nDCG@10)

Task	MRE-T1
Biology	74.2
Earth Science	72.2
Economics	57.3
Psychology	71.3
Robotics	51.6
StackOverflow	51.4
Sustainable Living	66.2
Pony	33.9
Average	35.1

Comparison with Other Models (Short, Single Model Only)

Model	Size	BRIGHT Short nDCG@10
MRE-T1	~4B	39.6
BGE-Reasoner-Embed-0928	8B	38.1
Seed1.5-Embedding	MoE	27.2
gte-Qwen1.5-7B-instruct	7B	22.5
GritLM-7B	7B	21.0
instructor-xl	1.5B	18.9
SFR-Embedding-Mistral	7B	18.3
e5-mistral-7b-instruct	7B	17.9

Comparison with Other Models (Long, Single Model Only)

Model	Size	BRIGHT Long nDCG@10
MRE-T1	~4B	35.1
Google-Gecko-Text-Embedding-004	—	33.2
gte-Qwen1.5-7B-instruct	7B	27.8
SFR-Embedding-Mistral	7B	26.0
e5-mistral-7b-instruct	7B	25.5
voyage-large-2-instruct	—	24.6
Cohere-embed-english-v3.0	—	18.4
bge-large-en-v1.5	335M	14.8

Usage

MRE-T1 uses task-specific system prompts for reasoning-enhanced retrieval. Each query is processed with a domain-specific instruction, and the model generates a reasoning chain followed by a special <emb_token> whose representation is used as the query embedding.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "ForwardAILabs/MRE-T1"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")

# Task-specific system prompts
TASK_PROMPTS = {
    "biology": "Given a Biology post, extract and briefly describe the core underlying principle or mechanism of this biology question. You MUST end every response with <emb_token>.",
    "earth_science": "Given an Earth Science post, identify the type of Earth science question and briefly describe the core principle for solving it. You MUST end every response with <emb_token>.",
    "economics": "Given an Economics post, analyze the user's core blind spot and the applicable economic analysis framework. You MUST end every response with <emb_token>.",
    "psychology": "Given a Psychology post, extract the user's blind spot and key psychological concepts. You MUST end every response with <emb_token>.",
    "robotics": "Given a Robotics post, diagnose the core issue within the robotics environment and error logs, and point out the applicable technical principles. You MUST end every response with <emb_token>.",
    "stackoverflow": "Given a Stack Overflow post, extract the core underlying technical principle for solving the code error. You MUST end every response with <emb_token>.",
    "sustainable_living": "Given a Sustainable Living post, identify the key scientific concepts and background knowledge required for a closed-loop solution to the life phenomenon or practice. You MUST end every response with <emb_token>.",
    "leetcode": "Given a Coding problem, extract the core algorithm principle (or data structure) and general problem-solving approach. You MUST end every response with <emb_token>.",
    "pony": "Given a Pony question, locate the core knowledge points from the Pony language official documentation needed to solve the code completion problem. You MUST end every response with <emb_token>.",
    "aops": "Given a Math problem, analyze the problem type characteristics and core examination principles of this math competition problem. You MUST end every response with <emb_token>.",
    "theoremqa_questions": "Given a Math problem, analyze the problem type characteristics and core examination principles of this math competition problem. You MUST end every response with <emb_token>.",
    "theoremqa_theorems": "Given a Math problem, distill the core mathematical principles and problem-solving techniques required for the real-world scenario. You MUST end every response with <emb_token>.",
}

# Example: Generate reasoning-enhanced query embedding
task = "stackoverflow"
query = "How to fix a segmentation fault when using shared_ptr in a multithreaded C++ application?"

messages = [
    {"role": "system", "content": TASK_PROMPTS[task]},
    {"role": "user", "content": query}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs, output_hidden_states=True)
    # Use the last hidden state at the <emb_token> position as the embedding
    embedding = outputs.hidden_states[-1][0, -1, :]

print(f"Embedding shape: {embedding.shape}")

Training

MRE-T1 is trained using a two-stage approach on the Qwen3-4B base model:

1. Stage 1: Supervised fine-tuning with task-specific reasoning prompts
2. Stage 2: Reinforcement learning to optimize retrieval quality

Training data is curated from diverse reasoning-intensive domains including mathematics, science, programming, and social sciences.

Evaluation

Evaluated on BRIGHT (Bridging Reasoning and Information Gathering with Holistic Thinking), a benchmark specifically designed to test retrieval models on tasks requiring complex reasoning.

Citation

If you use MRE-T1 in your research, please cite:

@misc{mre-t1-2026,
  title={MRE-T1: Reasoning-Enhanced Retrieval Model},
  author={Forward AI},
  year={2026},
  url={https://huggingface.co/ForwardAILabs/MRE-T1}
}

License

Apache 2.0