README.md

---
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
tags:
  - pddl
  - planning
  - blocksworld
  - robotics
  - chain-of-thought
  - self-criteach
base_model:
  - Qwen/Qwen3-4B-Instruct-2507
  - meta-llama/Llama-3.1-8B-Instruct
datasets:
  - Self-CriTeach/pddl-planning-data
---

# SCT — Self-CriTeach Checkpoints

Trained checkpoints from the paper **[Self-CriTeach: LLM Self-Teaching and Self-Critiquing for Improving Robotic Planning via Automated Domain Generation](https://arxiv.org/abs/2509.21543)**.

Self-CriTeach is a self-teaching framework: the base LLM auto-generates PDDL planning domains, uses them to produce CoT supervision and structured RL rewards, and is then post-trained on the result. This repository bundles **both released model families** (Qwen3-4B and Llama-3.1-8B) plus their intermediate training checkpoints in one place, organized by subfolder.

- **Code:** https://github.com/markli1hoshipu/Plan_LLM
- **Dataset:** [Self-CriTeach/pddl-planning-data](https://huggingface.co/datasets/Self-CriTeach/pddl-planning-data)
- **Project page:** https://markli1hoshipu.github.io/Plan_LLM/

## Quick start

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

# default models (latest available checkpoint per backbone):
tok = AutoTokenizer.from_pretrained("Self-CriTeach/SCT", subfolder="Qwen3-4B")
mdl = AutoModelForCausalLM.from_pretrained("Self-CriTeach/SCT", subfolder="Qwen3-4B")

# or the larger backbone:
tok = AutoTokenizer.from_pretrained("Self-CriTeach/SCT", subfolder="Llama-3.1-8B")
mdl = AutoModelForCausalLM.from_pretrained("Self-CriTeach/SCT", subfolder="Llama-3.1-8B")
```

The PDDL problem format and action vocabulary are documented in [`configs/prompts/eval_user_prompt_template.md`](https://github.com/markli1hoshipu/Plan_LLM/blob/main/configs/prompts/eval_user_prompt_template.md) of the code repository.

## Subfolders

### Qwen3-4B (base: Qwen/Qwen3-4B-Instruct-2507)

| Subfolder | Step | Size | Notes |
|---|---:|---:|---|
| `Qwen3-4B/` | 2000 | 8.0 GB | **Latest available checkpoint** (default). |
| `Qwen3-4B-step1600/` | 1600 | 8.0 GB | Earlier intermediate. |
| `Qwen3-4B-step1200/` | 1200 | 8.0 GB | Earlier intermediate. |

> **Disclosure on the Qwen3-4B checkpoint provenance.** The training run reached step 2572, but the final checkpoint files on disk were corrupted during save (one shard missing, index empty). The released `Qwen3-4B/` here is **step 2000** — the latest fully-intact snapshot. Numbers obtained when running this checkpoint may differ slightly from the paper's headline numbers for SCT-4B.

### Llama-3.1-8B (base: meta-llama/Llama-3.1-8B-Instruct)

| Subfolder | Step | Size | Notes |
|---|---:|---:|---|
| `Llama-3.1-8B/` | 3102 (final) | 16.1 GB | **Final published checkpoint** (default). |
| `Llama-3.1-8B-step2800/` | 2800 | 16.1 GB | Intermediate. |
| `Llama-3.1-8B-step2400/` | 2400 | 16.1 GB | Intermediate. |
| `Llama-3.1-8B-step2000/` | 2000 | 16.1 GB | Intermediate. |
| `Llama-3.1-8B-step1600/` | 1600 | 16.1 GB | Intermediate. |

The intermediates are provided for researchers studying training dynamics. Most users should use the default (`Llama-3.1-8B/`).

## Reproducing evaluation

Use the `Self-CriTeach/pddl-planning-data` `eval` split:

```bash
git clone https://github.com/markli1hoshipu/Plan_LLM.git
cd Plan_LLM
pip install -r requirements.txt

python scripts/evaluation/eval.py \
    --model Self-CriTeach/SCT \
    --data_file <(huggingface-cli download Self-CriTeach/pddl-planning-data eval/align_data_eval.jsonl --repo-type dataset) \
    --experiment_folder results/sct_4b \
    --gpus 0,1
# (use --model_subfolder if you fork eval.py to forward `subfolder=` — see GitHub README)
```

## Limitations

- Trained only on Blocksworld-family planning problems; performance on non-Blocksworld PDDL domains is untested.
- Inference is sensitive to the exact prompt template — use `configs/prompts/eval_user_prompt_template.md` from the code repository verbatim for reproducible results.
- The full RL-post-trained variants (`SCT_CPO`, `SCT_DPO`, `SCT_LCCS` in the paper's ablations) are **not** included — only the main checkpoints are released.

## Citation

```bibtex
@article{huang2025selfcriteach,
  title         = {Self-CriTeach: LLM Self-Teaching and Self-Critiquing for Improving Robotic Planning via Automated Domain Generation},
  author        = {Huang, Jinbang and Li, Zhiyuan and Hu, Yuanzhao and Zhang, Zhanguang and Coates, Mark and Quan, Xingyue and Zhang, Yingxue},
  journal       = {arXiv preprint arXiv:2509.21543},
  year          = {2025},
  url           = {https://arxiv.org/abs/2509.21543}
}
```

## License

Apache 2.0. Note that the base models (Qwen3-4B and Llama-3.1-8B) carry their own licenses; consult [Qwen's terms](https://huggingface.co/Qwen) and [Meta's Llama 3.1 license](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) before deploying.