CaPtain-4B-SFT

CaPtain-4B-SFT is the supervised fine-tuning (SFT) stage of CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents. It is Qwen3.5-4B fine-tuned on synthetic agent trajectories collected in CaPtain-Harness. It is the initialisation and the KL reference of the RL stage, which produces CaPtain-4B. For the best robot performance, use CaPtain-4B. Use this checkpoint to reproduce or modify the RL stage, or as an SFT baseline.

What the model is

• A code-writing agent, not a VLA. The model never outputs actions directly. At every request it writes Python for the harness's single python tool: a persistent, sandboxed Python 3.11 session. The robot API in that session has 22 low-level capabilities (perception, geometric measurement, IK-level guarded motion) plus finish(), and no grasp or place macros.
• What it sees: camera images, its own code and output, and one-line receipts of its robot calls.
• What it never sees: object poses and the success predicate.
• Perception services. SAM 3 segmentation and Molmo2-8B pointing run behind the harness tools.
• Format. bf16 safetensors with the Qwen3_5ForConditionalGeneration architecture and an untied lm_head. The tokenizer, processor and chat template are the same as Qwen3.5-4B. The vision tower is unchanged from the base model: it was frozen during SFT.

How to use

Use it exactly like CaPtain-4B, inside CaPtain-Harness.

vllm serve YijiaFan/CaPtain-4B-SFT --served-model-name captain-4b --dtype bfloat16 --max-model-len 81920 \
  --enable-prefix-caching --limit-mm-per-prompt '{"image":12}' --max-num-seqs 16 \
  --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_xml --port 8600   # vLLM 0.29

# in a CaPtain-Harness checkout (https://github.com/waltstephen/CaPtain-Harness, installed as in INSTALL.md):
services/start_perception.sh                                    # SAM 3 :8114 + Molmo2-8B :8122
export POLICY_URL=http://127.0.0.1:8600/v1 STUDENT_PYTHON=~/envs/student-py311/bin/python EGL_DEVICE=0
eval/run_episode.sh libero_spatial 0 11 runs/demo

The paper's evaluation protocol:

• sampling T = 1.0, top_p = 1.0, thinking on;
• budgets per episode: 60 model requests, 1,080 s and 150 physical actions;
• context: a 64k-token window with compaction.

To start RL from this checkpoint, see rl/README.md in the CaPtain repository.

Prompt format

The model was trained on the harness's exact request template:

• the system prompt and environment context;
• TASK.md, inlined in the system prompt;
• the python tool schema (python-runtime/v1);
• receipts, compaction notes and image placement.

The released SFT data show this template row by row. The model uses the standard Qwen3.5 chat template, with <think> reasoning and XML tool calls. Run it through CaPtain-Harness rather than with hand-written prompts, and do not change model-visible text when evaluating it.

Results

Success rates (%) in simulation, host / strict. Strict success also requires that the agent called finish() itself. The LIBERO row uses held-out official initial states 11–16 of the 40 tasks of the four standard suites.

The zero-shot transfer results of the paper (RoboTwin 2.0 22.6 on the official Hard protocol, SimplerEnv WidowX 83.3, CaP-Bench 75.0, RoboDojo Score 1.7) were measured with CaPtain-4B, not with this checkpoint.

Training

• Base: Qwen3.5-4B, with the lm_head untied (sft/scripts/untie_base.py).
• Data: CaPtain-SFT-Data:
  • synthetic agent trajectories collected in CaPtain-Harness, generated with frontier models, plus successful episodes of the student itself;
  • visual QA at loss weight 0.5.
• Supervision: only assistant turns. A text-hint mask (p = 0.2) replaces earlier mark_point pixel coordinates with <masked>, so the model has to read the image.
• Optimisation: full fine-tuning of the language model with the vision tower frozen. Peak LR 1e-5, 30 warmup steps, cosine schedule. One row per rank on 16 ranks, with a constant global per-token loss normaliser. DeepSpeed ZeRO-3, bf16, gradient clipping 1.0.
• Length: 2,435 steps (1.5 epochs).

The trainer, launch script and exact configuration are in the CaPtain repository (sft/).

Limitations

• Simulation-trained. The SFT trajectories are simulated episodes, almost all on LIBERO. The model was not trained on real-robot data.
• Weaker than the RL model. It is clearly worse than CaPtain-4B on every benchmark above. Missed finishes and long-horizon or articulated tasks are its main failures.
• Inputs. It depends on the harness's perception services (SAM 3, Molmo2-8B), depth, camera calibration, and the exact prompt and tool format.
• One arm at a time. Two-arm coordination is not supported.
• Research artifact. Not validated for safety-critical use or for unsupervised use on physical robots.

License

Apache-2.0, the license of the base model Qwen3.5-4B. The SFT data have their own terms; see the dataset card. Components you run with the model (LIBERO, SAM 3, Molmo2, simulators) keep their own licenses.

Citation

@article{fan2026captain,
  title   = {CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents},
  author  = {Fan, Yijia and He, Xilin and Jiang, Yilei and Wu, Dongming and Wang, Jiaxu and Yue, Xiangyu},
  journal = {arXiv preprint},
  year    = {2026}
}

Contact: Xiangyu Yue (xyyue@ie.cuhk.edu.hk), MMLab, The Chinese University of Hong Kong.