SeekJudge-9B

SeekJudge-9B

SeekJudge-9B is the trained judge model of SeekJudge, a reward framework for reinforcement learning in computer-use agents. Given a task goal and a recorded trajectory (screenshots plus actions), it decides whether the goal was achieved and emits per-step quality labels in the <answer_overall> / <answer_step> format.

The model is a judge, not an agent. It does not produce GUI actions.

Code and resources

The repository README covers serving the model, running it as a batch judge over trajectory datasets, and hosting it as an HTTP reward server for online RL training. This checkpoint requires seek.trained: True in the SeekJudge configuration, which selects the parser for the trained output format.

Model size

Architecture follows the Qwen3.5 multimodal stack: 32 language layers mixing linear attention with full attention every 4th layer, hidden size 4096, 16 attention heads with 4 KV heads, plus a 27-layer SigLIP-style vision tower (hidden size 1152, patch size 16) projecting to 4096.

Training cost

Peak memory stays low because DeepSpeed ZeRO-3 offloads both optimizer states and parameters to CPU, which trades memory for the step time above.

Training configuration

Full-parameter supervised fine-tuning of the language model on top of Qwen/Qwen3.5-9B, with the vision encoder and the aligner frozen. Run with ms-swift 4.1.0.dev0 on transformers 5.3.0.

Data volume

The mixture combines trajectory-level judging targets, per-step analysis targets, and tool-query targets, so that one model serves every stage of the SeekJudge pipeline.

Final training metrics

Training loss 0.246 and token accuracy 0.918 at step 2,840; mean loss over the whole run 0.380.

License

Apache-2.0, inherited from the Qwen3.5-9B base model. The SeekJudge codebase is MIT-licensed.