amazon / LAR-27B

huggingface.co
Total runs: 344
24-hour runs: 7
7-day runs: 7
30-day runs: 334
Model's Last Updated: October 23 2026

Introduction of LAR-27B

Model Details of LAR-27B

LAR-27B

This is the official model repository for Agentic RL Model with Process Reward with Lean 4 (LAR) .

Model performance
Main Results

ResultPlot

Model Size SWE-Bench-Verified TB-2.0 TB-2.1
LAR-9B 9B 64.2% 32.8% 29.5%
LAR-27B 27B 84.2% 68.2% 77.3%
1. Install dependencies
1.1 Install environment
# Install the corresponding environment
# (run from the repository root; needs python3.12 + venv, git, docker with compose v2 (user in the docker group), sudo,
#  an NVIDIA driver and CUDA toolkit for CUDA 13; MODEL = local LAR-27B checkpoint, WORK = work dir on a fast local disk)
export MODEL=amazon/LAR-27B WORK=/path/to/local/disk/tb21
python3.12 -m venv ~/.venvs/lar-serve
~/.venvs/lar-serve/bin/pip install -r PSWF/EvaluationKit/TB-2.1/requirements/serve.txt ./PSWF/EvaluationKit/TB-2.1
python3.12 -m venv ~/.venvs/lar-eval
~/.venvs/lar-eval/bin/pip install -r PSWF/EvaluationKit/TB-2.1/requirements/eval.txt ./PSWF/Harness/Terminus-2 ./PSWF/EvaluationKit/TB-2.1
~/.venvs/lar-eval/bin/python -m pswf_harbor_patches --tokenizer-dir $MODEL
1.2 Init TB-2.1 containers
# Initialize the TB-2.1 containers
~/.venvs/lar-eval/bin/python -m tb21_eval.prepare --work-dir $WORK
sudo ~/.venvs/lar-eval/bin/python -m tb21_eval.netguard up --work-dir $WORK
~/.venvs/lar-eval/bin/python -m tb21_eval.netguard probe --work-dir $WORK
2. Run TB-2.1 evaluation using PSWF with Terminus-2
# Run the evaluation
~/.venvs/lar-serve/bin/python -m tb21_eval.serve up --model $MODEL --work-dir $WORK
~/.venvs/lar-eval/bin/python -m tb21_eval.make_job --model $MODEL --work-dir $WORK --run-dir $WORK/runs/x5 --n-attempts 5 --n-concurrent 40
setsid nohup ~/.venvs/lar-eval/bin/harbor run -c $WORK/runs/x5/job.json --env-file $WORK/runs/x5/harbor.env > $WORK/runs/x5/harbor.log 2>&1 &
# ~16 h in the background; score at any time (if harbor was interrupted: ~/.venvs/lar-eval/bin/python -m tb21_eval.resume --run-dir $WORK/runs/x5)
~/.venvs/lar-eval/bin/python -m tb21_eval.score $WORK/runs/x5
Training Data and Methodology

The released checkpoint is post-trained from Qwen/Qwen3.8-27B (licensed under Apache License 2.0) using Lean4AgenticRL process reward methods. This version was trained only on a filtered subset of SWE-Rebench containing software-engineering task examples from public code repositories. The underlying repository licenses were verified at the pinned base commits, and only examples meeting the license-filtering criteria were retained.

Responsible AI Considerations

At Amazon, we are committed to developing AI responsibly and take a people-centric approach that prioritizes education, science, and our customers, to integrate responsible AI across the end-to-end AI lifecycle. We believe the use of AI must respect the rule of law and human rights, and we encourage the safe and responsible development of AI. When downloaded or used in accordance with AWS Responsible AI Policy , developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

Please report model quality, risk, security vulnerabilities or Amazon AI Concerns here .

Reference

If you find our work useful, please cite it using the BibTeX entry below. This entry currently links to the PDF hosted on GitHub and will be updated once the arXiv version is available.

@misc{wang2026lean4agenticrl,
      title={{Lean4AgenticRL}: Advancing Agentic {RL} with Verifiable Multi-level Process Rewards},
      author={Ruida Wang and Gerald Friedland and Tong Zhang and Chris Kong},
      year={2026},
      note={Preprint},
}

Runs of amazon LAR-27B on huggingface.co

344
Total runs
7
24-hour runs
7
3-day runs
7
7-day runs
334
30-day runs

More Information About LAR-27B huggingface.co Model

More LAR-27B license Visit here:

https://choosealicense.com/licenses/apache-2.0

LAR-27B huggingface.co

LAR-27B huggingface.co is an AI model on huggingface.co that provides LAR-27B's model effect (), which can be used instantly with this amazon LAR-27B model. huggingface.co supports a free trial of the LAR-27B model, and also provides paid use of the LAR-27B. Support call LAR-27B model through api, including Node.js, Python, http.

LAR-27B huggingface.co Url

https://huggingface.co/amazon/LAR-27B

amazon LAR-27B online free

LAR-27B huggingface.co is an online trial and call api platform, which integrates LAR-27B's modeling effects, including api services, and provides a free online trial of LAR-27B, you can try LAR-27B online for free by clicking the link below.

amazon LAR-27B online free url in huggingface.co:

https://huggingface.co/amazon/LAR-27B

LAR-27B install

LAR-27B is an open source model from GitHub that offers a free installation service, and any user can find LAR-27B on GitHub to install. At the same time, huggingface.co provides the effect of LAR-27B install, users can directly use LAR-27B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

LAR-27B install url in huggingface.co:

https://huggingface.co/amazon/LAR-27B

Url of LAR-27B

LAR-27B huggingface.co Url

Provider of LAR-27B huggingface.co

amazon
ORGANIZATIONS

Other API from amazon

huggingface.co

Total runs: 8.1M
Run Growth: -7.5M
Growth Rate: -92.20%
Updated:June 05 2026
huggingface.co

Total runs: 725.4K
Run Growth: 316.2K
Growth Rate: 43.59%
Updated:November 21 2025
huggingface.co

Total runs: 489.6K
Run Growth: -6.8K
Growth Rate: -1.39%
Updated:November 21 2025
huggingface.co

Total runs: 425.5K
Run Growth: -474.1K
Growth Rate: -111.41%
Updated:November 21 2025
huggingface.co

Total runs: 43.7K
Run Growth: -11.4K
Growth Rate: -26.10%
Updated:November 21 2025
huggingface.co

Total runs: 1.2K
Run Growth: -501
Growth Rate: -41.96%
Updated:October 07 2026
huggingface.co

Total runs: 799
Run Growth: 378
Growth Rate: 47.31%
Updated:October 03 2026
huggingface.co

Total runs: 295
Run Growth: -1.2K
Growth Rate: -412.20%
Updated:May 16 2024
huggingface.co

Total runs: 215
Run Growth: 53
Growth Rate: 24.88%
Updated:November 17 2023
huggingface.co

Total runs: 199
Run Growth: -20
Growth Rate: -10.05%
Updated:May 30 2025
huggingface.co

Total runs: 144
Run Growth: 21
Growth Rate: 15.00%
Updated:March 01 2024
huggingface.co

Total runs: 88
Run Growth: 82
Growth Rate: 93.18%
Updated:October 23 2026