- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes a trajectory supervision framework for training vision language game agents to plan, act, and verify their execution. The method segments gameplay trajectories into local plans and constructs supervision signals for action prediction and execution status verification. Experiments on Tetris, Sokoban, and MiniGrid show improvements over direct action prediction, Plan-as-CoT, and Plan-Chunk baselines across multiple vision language backbones.
Critical strengths
- The paper presents a straightforward way to extract planning and verification supervision from existing gameplay trajectories.
- The method outperforms several baselines across three games and multiple model backbones. The ablation studies also provide useful evidence for the proposed training strategy.
Critical weaknesses
- Limited novelty.The main approach largely combines existing ideas in hierarchical planning, imitation learning, and execution verification. The technical contribution is relatively incremental, with limited new insights beyond restructuring trajectory data for supervised fine tuning.
- Limited evaluation complexity and generalization.The experiments focus on three relatively simple and structured games. It remains unclear whether the proposed method can generalize to a broader range of games, which deserves further investigation.
Questions for authors
What is the key technical distinction between the proposed framework and existing hierarchical imitation learning or plan conditioned policy learning methods? Can the authors provide evidence that the method works in more complex environments?
The authors did not submit a rebuttal, so I'm going to keep my original score unchanged.