xtools-at

Qwen3.5-9B-Reasoning-Generator

README

License: apache-2.0

💡 What it does

Trace inversion uses a known problem and answer to generate a plausible reasoning trace connecting the two. Rather than expanding compressed reasoning bubbles, the model reconstructs a concise explanation from the available endpoints, producing output in a <think>...</think> block.

The model is intended for research and synthetic-data workflows rather than as a general-purpose answer model. Generated traces are limited to 1,200 characters to encourage concise reasoning.

The generated trace is not the original hidden reasoning of Qwen3.8-Max or any other source model. It is a model-generated reconstruction and should be labelled as synthetic.

📚 Training data

The model was trained on a trace-inverted version of saidutta69/qwen3.8-max-distillation-50k-clean, a cleaned collection of reasoning data generated by Qwen3.8-Max (qwen3.8-max-preview).

The dataset uses randomly sampled entries to construct a question-and-answer-conditioned reasoning-generation task:

10,000 training entries
500 evaluation entries

The task uses the following inputs and targets:

input — original problem or context
output — known final answer
inverted_reasoning — target synthetic reasoning trace

Unlike the bubble-conditioned Trace Inverter, no reasoning_bubble is supplied to the model. Instead, the training process uses the question and final answer to generate a plausible reasoning trace, with each target limited to 1,200 characters.

This setup explores whether models can learn to produce useful reasoning explanations from Qwen3.8-Max-derived problems and answers without requiring pre-existing reasoning information at inference time.

🛠️ Usage

Provide the model with the problem and its known final answer. No reasoning bubbles are required.

Example prompt:

System

text

You are an advanced reasoning- and chain-of thought generation model. Given a problem, a final answer, and several compressed reasoning bubbles, reconstruct a detailed reasoning trace that could plausibly lead to the final answer. Follow these rules:- Work backwards from the answer to the problem.- Expand the answer into coherent reasoning while preserving the original logical order.- Keep the trace consistent with the problem and the final answer.- Do not introduce unrelated methods, new assumptions, or a different conclusion.- Output only the reconstructed reasoning trace wrapped in <think>...</think>.

User

text

Problem:{problem} Model's final answer:{final_answer} Reconstruct the full reasoning trace.

Expected output shape

text

<think>{synthetic reasoning trace}</think>

Use the model's supported Qwen3.5 processor/model classes and chat template for inference. Generation settings can affect trace length and style, so validate outputs before adding them to a training dataset.

🎯 Intended uses

Generating concise synthetic reasoning traces from problems and known final answers.
Research into trace inversion and reasoning supervision without reasoning bubbles.
Creating draft examples for downstream supervised fine-tuning, after careful filtering and verification.
Exploring reasoning distillation using Qwen3.8-Max-derived data.

⚠️ Limitations & responsible use

Synthetic, not recovered: Outputs are reconstructions, not verified private reasoning from Qwen3.8-Max or another source model.
Answer-conditioned: The model uses the supplied final answer as a constraint and may produce a convincing explanation for an incorrect answer.
No reasoning bubbles: This model is designed to generate traces without intermediate reasoning summaries. It does not require bubbles as part of its expected input.
Length-constrained: The 1,200-character target limit favors concise explanations and may restrict the detail available for more complex problems.
Verify before reuse: Check calculations, run code where relevant, and fact-check claims before using generated traces as supervision.
Research use: Do not rely on generated traces as proof of correctness or for high-stakes medical, legal, or financial decisions. Follow applicable model and dataset terms when using or redistributing outputs.

xtools-at/Qwen3.5-4B-Reasoning-Generator — 4B version of this model
xtools-at/Qwen3.5-9B-Trace-Inverter — bubble-conditioned trace-inversion model.
amkkk/Trace-Inverter-4B-NoBubble — no-bubble trace-inversion reference model.
saidutta69/qwen3.8-max-distillation-50k-clean — Qwen3.8-Max-derived source dataset.
Zhang, Morris, and Shmatikov, How to Steal Reasoning Without Reasoning Traces, arXiv:2603.07267 (2026).

bibtex

@misc{zhang2026stealreasoning,  title         = {How to Steal Reasoning Without Reasoning Traces},  author        = {Tingwei Zhang and John X. Morris and Vitaly Shmatikov},  year          = {2026},  eprint        = {2603.07267},  archivePrefix = {arXiv}}

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

xtools-at

Model Tree

Base

xtools-at/Qwen3.5-9B-Claude-3xMerge-UNCENSORED-heretic

Adapter

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

💡 What it does

The model is intended for research and synthetic-data workflows rather than as a general-purpose answer model. Generated traces are limited to 1,200 characters to encourage concise reasoning.

The generated trace is not the original hidden reasoning of Qwen3.8-Max or any other source model. It is a model-generated reconstruction and should be labelled as synthetic.

📚 Training data

The model was trained on a trace-inverted version of saidutta69/qwen3.8-max-distillation-50k-clean, a cleaned collection of reasoning data generated by Qwen3.8-Max (qwen3.8-max-preview).

The dataset uses randomly sampled entries to construct a question-and-answer-conditioned reasoning-generation task:

10,000 training entries
500 evaluation entries

The task uses the following inputs and targets:

input — original problem or context
output — known final answer
inverted_reasoning — target synthetic reasoning trace

🛠️ Usage

Provide the model with the problem and its known final answer. No reasoning bubbles are required.

Example prompt:

System

text

You are an advanced reasoning- and chain-of thought generation model. Given a problem, a final answer, and several compressed reasoning bubbles, reconstruct a detailed reasoning trace that could plausibly lead to the final answer.Follow these rules:- Work backwards from the answer to the problem.- Expand the answer into coherent reasoning while preserving the original logical order.- Keep the trace consistent with the problem and the final answer.- Do not introduce unrelated methods, new assumptions, or a different conclusion.- Output only the reconstructed reasoning trace wrapped in <think>...</think>.

You are an advanced reasoning- and chain-of thought generation model. Given a problem, a final answer, and several compressed reasoning bubbles, reconstruct a detailed reasoning trace that could plausibly lead to the final answer. Follow these rules:- Work backwards from the answer to the problem.- Expand the answer into coherent reasoning while preserving the original logical order.- Keep the trace consistent with the problem and the final answer.- Do not introduce unrelated methods, new assumptions, or a different conclusion.- Output only the reconstructed reasoning trace wrapped in <think>...</think>.

User

text

Problem:{problem}Model's final answer:{final_answer}Reconstruct the full reasoning trace.

Problem:{problem} Model's final answer:{final_answer} Reconstruct the full reasoning trace.

Expected output shape

text

<think>{synthetic reasoning trace}</think>

🎯 Intended uses

Generating concise synthetic reasoning traces from problems and known final answers.
Research into trace inversion and reasoning supervision without reasoning bubbles.
Creating draft examples for downstream supervised fine-tuning, after careful filtering and verification.
Exploring reasoning distillation using Qwen3.8-Max-derived data.

⚠️ Limitations & responsible use

Synthetic, not recovered: Outputs are reconstructions, not verified private reasoning from Qwen3.8-Max or another source model.
Answer-conditioned: The model uses the supplied final answer as a constraint and may produce a convincing explanation for an incorrect answer.
No reasoning bubbles: This model is designed to generate traces without intermediate reasoning summaries. It does not require bubbles as part of its expected input.
Length-constrained: The 1,200-character target limit favors concise explanations and may restrict the detail available for more complex problems.
Verify before reuse: Check calculations, run code where relevant, and fact-check claims before using generated traces as supervision.
Research use: Do not rely on generated traces as proof of correctness or for high-stakes medical, legal, or financial decisions. Follow applicable model and dataset terms when using or redistributing outputs.

xtools-at/Qwen3.5-4B-Reasoning-Generator — 4B version of this model
xtools-at/Qwen3.5-9B-Trace-Inverter — bubble-conditioned trace-inversion model.
amkkk/Trace-Inverter-4B-NoBubble — no-bubble trace-inversion reference model.
saidutta69/qwen3.8-max-distillation-50k-clean — Qwen3.8-Max-derived source dataset.
Zhang, Morris, and Shmatikov, How to Steal Reasoning Without Reasoning Traces, arXiv:2603.07267 (2026).

bibtex

@misc{zhang2026stealreasoning,  title         = {How to Steal Reasoning Without Reasoning Traces},  author        = {Tingwei Zhang and John X. Morris and Vitaly Shmatikov},  year          = {2026},  eprint        = {2603.07267},  archivePrefix = {arXiv}}

@misc{zhang2026stealreasoning,  title         = {How to Steal Reasoning Without Reasoning Traces},  author        = {Tingwei Zhang and John X. Morris and Vitaly Shmatikov},  year          = {2026},  eprint        = {2603.07267},  archivePrefix = {arXiv}}

Qwen3.5-9B-Reasoning-Generator

README

💡 What it does

📚 Training data

🛠️ Usage

System

User

Expected output shape

🎯 Intended uses

⚠️ Limitations & responsible use

🔗 Related work

Explore FriendliAI today

README

💡 What it does

📚 Training data

🛠️ Usage

System

User

Expected output shape

🎯 Intended uses

⚠️ Limitations & responsible use

🔗 Related work