ViDecide: Teaching Video Diffusion Models to Reason and Plan Step by Step
Organizations: S-Lab, Nanyang Technological University · KlingAI Research · CUHK
Abstract
Current leading video generation models can synthesize highly realistic videos, while still frequently violating physical and logical constraints in multi-step reasoning and planning, even after training with large-scale reasoning data or existing diffusion RL methods. We attribute these failures to the conventional video training paradigm, which treats a solution as a fixed-length clip rather than a chain of decisions. We present ViDecide, a decision-centric framework that trains video diffusion models to predict state transitions causally and decide when to stop, with a decision-focused training schedule. We further propose Corrective Fine-tuning (CFT), which corrects failed decisions by mapping their noise to the model's own successful continuations, achieving stable improvement without policy-gradient optimization. Across abstract games, planning tasks, and a new benchmark of multi-step robot planning, ViDecide achieves an average strict success rate of 83.8%, far above 23.3% for standard fine-tuning and 67.8% for the strongest prior method, and generalizes to larger puzzles and unseen layouts. Our framework therefore unlocks greater potential for video generation models as reliable reasoners and planners in the visual world. Project page: https://kevin-thu.github.io/ViDecide.
Figures & tables
| Wan2.2-5B fine-tuned | DiT-B trained from scratch | |||||
| Method | FlowFree | Sokoban | VBVR-MultiStep | RoboTwin-Plan | FlowFree | Sokoban |
| Zero-shot video generators | ||||||
| Seedance 2.5 † | 0.0 | 5.0 | 20.0 | 6.7 | – | – |
| Veo 3.1 † | 0.0 | 5.0 | 0.0 | 0.0 | – | – |
| Wan2.2-5B | 0.0 | 0.0 | 0.0 | 0.0 | – | – |
| VBVR-Wan2.2-A14B | 0.0 | 0.0 | 11.3 | 0.0 | – | – |
| Method | Hanoi | Ordinal | Sliding | Snake | Sokoban | TSP |
|---|---|---|---|---|---|---|
| Fixed-length generation | ||||||
| Bidirectional | 8.0 | 2.0 | 9.0 | 5.0 | 39.0 | 71.0 |
| HDR [ 38 ] | 13.0 | 27.0 | 12.0 | 1.0 | 19.0 | 72.0 |
| S2PD [ 21 ] | 21.0 | 94.0 | 52.0 | 70.0 | 64.0 | 86.0 |
| Causal generation with adaptive termination | ||||||
| Ours ( ) | 33.0 | 94.0 | 47.0 | 37.0 | 51.0 | 85.0 |
| Blocks World | Tower of Hanoi | Color Sorting | ||||
| Method | Row | Triangle | Row | Triangle | Buffer | No buffer |
| Fixed-length generation | ||||||
| Bidirectional | 66.0 | 30.0 | 98.0 | 66.0 | 55.0 | 5.0 |
| HDR [ 38 ] | 86.0 | 56.7 | 90.0 | 72.0 | 75.0 | 35.0 |
| S2PD [ 21 ] | 79.0 | 46.3 | 92.0 | 84.0 | 80.0 | 54.0 |
| Causal generation with adaptive termination | ||||||
| Benchmark | |||
|---|---|---|---|
| Wan2.2-5B fine-tuned | |||
| FlowFree | 46.8 | 73.5 | 77.9 |
| Sokoban | 68.4 | 79.6 | 83.0 |
| VBVR-MultiStep | 44.0 | 70.3 | 74.8 |
| RoboTwin-Plan | 2.6 | 33.3 | 73.9 |
| DiT-B trained from scratch | |||
| Wan2.2-5B fine-tuned | DiT-B trained from scratch | |||||||||
| FlowFree | Sokoban | VBVR-MultiStep | RoboTwin-Plan | FlowFree | Sokoban | |||||
| Method | Test | Hard | Test | Hard | Test | Test | Test | Hard | Test | Hard |
| S2PD [ 21 ] | 68.1 | 41.2 | 75.7 | 38.2 | 64.5 | 62.9 | 41.2 | 25.6 | 56.4 | 11.6 |
| SFT model (ours) | 77.9 | 44.8 | 83.0 | 50.0 | 74.8 | 73.9 | 58.6 | 24.4 | 73.8 | 32.8 |
| + Continued SFT | 75.5 | 48.6 | 85.5 | 59.6 | 74.2 | 74.3 | 55.8 | 34.4 | 74.1 | 42.4 |
| Sample-level | ||||||||||
| FlowFree | Sokoban | |||
|---|---|---|---|---|
| Setting | Test | Hard | Test | Hard |
| CFT, round 1 | 84.4 | 52.0 | 90.8 | 78.2 |
| + same updates, round-1 data | 84.5 | 53.0 | 90.7 | 76.4 |
| + round 2 | 86.2 | 57.6 | 92.4 | 80.2 |
| Sokoban | FlowFree | RoboTwin-Plan | |||
|---|---|---|---|---|---|
| Method | 4 boxes | 5 boxes | 9 9 | Blocks 2 2 | Hanoi 2 2 |
| Bidirectional | 0.0 | 2.0 | 0.0 | 14.0 | 16.0 |
| Ours ( ) | 23.0 | 10.0 | 3.0 | 36.0 | 18.0 |
| Ours ( ) | 51.0 | 37.0 | 32.0 | 4.0 | 2.0 |
| + CFT (ours) | 74.0 | 54.0 | 38.0 | 32.0 | 14.0 |
| Benchmark | Task | Train | Test | Setting | Frames |
| VideoRLVR | Maze | 9,500 | 1,000 | 5–15 passages per side | 77 / 105 |
| FlowFree | 9,500 | 1,000 | – boards, 3–5 colors | 101 / 173 | |
| Sokoban | 9,500 | 1,000 | 1–3 boxes, 2–51 moves | 69 / 253 | |
| VBVR-MultiStep | Tower of Hanoi | 5,000 | 100 | 3–5 blocks, 1–11 moves | 97 / 193 |
| Ordinal Number Sequence | 5,000 | 100 | 3 numbers | 89 / 177 | |
| Sliding Puzzle | 5,000 | 100 | – boards, 7–15 moves | 69 / 105 |
| Sokoban | VBVR-MultiStep | |||
|---|---|---|---|---|
| Method | End state | Strict | Strict | + Shortest |
| Bidirectional | 98.2 | 50.8 | 24.3 | 22.3 |
| Ours ( ) | 84.5 | 75.0 | 65.2 | 57.8 |
| Ours ( ) | 83.5 | 83.0 | 85.7 | 74.8 |
| Wan2.2-5B | DiT-B | |||
| VideoRLVR | VBVR-MultiStep | RoboTwin-Plan | VideoRLVR | |
| Updates | 47,500 | 37,500 | 16,700 | 11,000 |
| Batch | 2 | 4 | 6 | 32 |
| Epochs | 10 | 5 | 10 | 37 |
| Peak learning rate | ||||
| Warmup / schedule | 500 / cosine | 500 / cosine | 500 / cosine | 500 / constant |
| Wan2.2-5B | DiT-B | |||||
| FlowFree | Sokoban | VBVR-MultiStep | RoboTwin-Plan | FlowFree | Sokoban | |
| Start model | ||||||
| Corrections | 8,483 (2,257) | 6,962 (2,747) | 10,937 (3,932) | 3,430 (1,258) | 9,633 (3,128) | 5,791 (1,802) |
| Updates | 7,600 | 6,200 | 9,800 | 3,200 | 1,000 | 1,000 |
| Batch | 3 | 3 | 3 | 3 | 32 | 32 |
| Peak learning rate | ||||||
| FlowFree | FlowFree-Hard | Sokoban | Sokoban-Hard | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Method | ||||||||||||
| SFT model (ours) | 77.9 | 90.8 | 96.1 | 44.8 | 59.4 | 72.2 | 83.0 | 88.7 | 92.0 | 50.0 | 64.2 | 73.8 |
| + Continued SFT | 75.5 | 89.6 | 94.6 | 48.6 | 60.4 | 73.4 | 85.5 | 90.3 | 93.2 | 59.6 | 73.0 | 82.2 |
| + Sample-level RFT | 83.2 | 92.9 | 96.6 | 50.2 | 63.0 | 76.6 | 90.1 | 93.1 | 94.8 | 61.6 | 75.2 | 83.4 |
| + Decision-level RFT | 80.1 | 91.7 | 96.6 | 52.0 | 67.2 | 80.0 | 89.8 | 94.0 | 96.2 | 73.8 | 83.4 | 88.0 |
| + CFT (ours) | 84.4 | 93.2 | 97.4 | 52.0 | 68.6 | 79.8 | 90.8 | 94.5 | 96.8 | 78.2 | 85.0 | 88.6 |
| Method | Hanoi | Ordinal | Sliding | Snake | Sokoban | TSP | All |
|---|---|---|---|---|---|---|---|
| SFT model (ours) | 37.0 | 97.0 | 61.0 | 86.0 | 75.0 | 93.0 | 74.8 |
| + Continued SFT | 32.0 | 97.0 | 62.0 | 85.0 | 75.0 | 94.0 | 74.2 |
| Sample-level | |||||||
| + Flow-GRPO | 30.0 | 97.0 | 59.0 | 87.0 | 70.0 | 96.0 | 73.2 |
| + DiffusionNFT | 32.0 | 96.0 | 57.0 | 85.0 | 72.0 | 94.0 | 72.7 |
| + RFT | 54.0 | 97.0 | 69.0 | 87.0 | 79.0 | 93.0 | 79.8 |
| Wan2.2-5B | DiT-B | |||
| Method | FlowFree | Sokoban | FlowFree | Sokoban |
| Bidirectional | 1.1 | 50.8 | 0.0 | 8.8 |
| HDR [ 38 ] | 11.6 | 45.9 | 0.4 | 10.3 |
| S2PD [ 21 ] | 68.1 | 75.7 | 41.2 | 56.4 |
| Ours, diffusion forcing | 69.9 | 81.8 | 59.6 | 58.1 |
| Ours, teacher forcing | 77.9 | 83.0 | 58.6 | 73.8 |
| FlowFree | Sokoban | VBVR-MultiStep | RoboTwin-Plan | ||||||
| Method | Steps | SSR | Time | SSR | Time | SSR | Time | SSR | Time |
| Bidirectional | 2 | 0.0 | 2.5 | 28.5 | 2.5 | 10.8 | 2.3 | 11.7 | 2.2 |
| 5 | 1.0 | 3.1 | 41.0 | 3.1 | 23.3 | 2.9 | 52.5 | 2.7 | |
| 10 | 1.5 | 4.1 | 42.5 | 4.0 | 25.8 | 3.8 | 65.8 | 3.5 | |
| 20 | 4.0 | 6.0 | 44.0 | 6.0 | 25.8 | 5.7 | 69.2 | 5.1 | |
| HDR | 5–50 | 9.0 | 188.2 | 34.0 | 184.2 | 27.5 | 180.4 | 67.5 | 140.8 |
| Sampling shift | ||||
|---|---|---|---|---|
| Benchmark | Training | 1 | 5 | 10 |
| FlowFree | 34.5 | 46.0 | 46.5 | |
| 67.0 | 71.5 | 69.0 | ||
| 73.5 | 73.0 | 70.5 | ||
| Sokoban | 55.0 | 57.0 | 59.0 | |
| 74.0 | 73.0 | 74.0 | ||
| Successful decision | Safe move | |||
|---|---|---|---|---|
| Method | Fresh | Failure noise | Fresh | Failure noise |
| SFT model (start) | 43.8 | 1.3 | 81.0 | 63.8 |
| + Continued SFT | 49.3 | 20.1 | 84.2 | 73.8 |
| + Sample-level RFT | 55.7 | 36.2 | 87.2 | 83.2 |
| + Decision-level RFT | 65.9 | 48.3 | 95.0 | 90.6 |
| + CFT (ours) | 67.9 | 57.0 | 95.0 | 93.3 |
| Wan2.2-5B | DiT-B | ||||
|---|---|---|---|---|---|
| Noise | Timesteps | Test | Hard | Test | Hard |
| Fresh | 80.1 | 52.0 | 59.0 | 28.0 | |
| Fresh | 80.8 | 48.6 | 62.1 | 27.0 | |
| Failed rollout | 83.6 | 53.6 | 63.4 | 25.4 | |
| Failed rollout | 84.4 | 52.0 | 65.6 | 27.2 | |
| Game | Test | Hard | Test | Hard | Test | Hard |
|---|---|---|---|---|---|---|
| FlowFree | 63.4 | 25.4 | 65.6 | 27.2 | 61.3 | 23.6 |
| Sokoban | 79.1 | 46.1 | 79.6 | 48.3 | 79.2 | 47.9 |
| FlowFree | Sokoban | ||
| Method | 9 9 | 4 boxes | 5 boxes |
| SFT model (ours) | 32.0 | 51.0 | 37.0 |
| + Continued SFT | 38.0 | 58.0 | 33.0 |
| Sample-level | |||
| + Flow-GRPO | 30.0 | 45.0 | 22.0 |
| + DiffusionNFT | 33.0 | 45.0 | 28.0 |
| Test set | Method | Success | Rule | Unfinished | Visual |
|---|---|---|---|---|---|
| Original | Ours ( ) | 73.9 | 7.7 | 7.7 | 10.7 |
| + Continued SFT | 74.3 | 8.9 | 8.6 | 8.3 | |
| + Sample-level RFT | 77.9 | 7.0 | 3.1 | 11.9 | |
| + Decision-level RFT | 70.7 | 6.1 | 5.4 | 17.7 | |
| + CFT (ours) | 78.0 | 4.9 | 4.1 | 13.0 | |
| New sets | Ours ( ) | 26.7 | 38.0 | 14.7 | 20.7 |
| Blocks World | Hanoi | Longer | |
|---|---|---|---|
| Method | 2 2 (50) | 2 2 (50) | plans (50) |
| Bidirectional | 14.0 | 16.0 | 0.0 |
| Ours ( ) | 36.0 | 18.0 | 26.0 |
| Ours ( ) | 4.0 | 2.0 | 22.0 |
| + CFT (ours) | 32.0 | 14.0 | 18.0 |
| FlowFree | Sokoban | |||
|---|---|---|---|---|
| Method | Test | Hard | Test | Hard |
| Qwen3.8-27B | 68.0 | 42.0 | 36.0 | 40.0 |
| Claude Opus 5.5 | 100.0 | 100.0 | 100.0 | 96.0 |
| ViDecide (video) | 82.0 | 66.0 | 90.0 | 82.0 |
| Benchmark | Task | Prompt |
| VideoRLVR | Maze | Solve the maze by drawing one continuous color path from the color start to the color goal without crossing a wall. |
| FlowFree | Fill the grid one cell at a time. Start at any colored endpoint and visit every remaining endpoint of that color. Then switch at an endpoint of a new color. Moves are horizontal or vertical, cannot cross or overlap, and every cell must be filled. Keep a single continuous walk across color changes: the next endpoint must be adjacent to the previous filled cell. | |
| Sokoban | Solve the Sokoban puzzle. Move the agent and push every box onto a target. Boxes cannot be pulled and walls cannot be crossed. | |
| VBVR-MultiStep | Tower of Hanoi | [Scenario] The image shows colored blocks arranged in stacks. There is a CURRENT state on the left and a TARGET state on the right. [Rules] 1. Only the topmost block of any stack can be moved at a time. 2. A move consists of lifting a block, moving it horizontally, and lowering it onto another stack or empty position. [Task] Generate a video solving the puzzle by transforming the CURRENT state to exactly match the TARGET state. Animate the blocks moving one by one, using the minimum total number of moves required. |
| Ordinal Number Sequence | [Scenario] The image shows a grid with a green start point, a red end point, and several yellow cells marked with sequential numbers (1, 2, 3…). An orange circular agent is positioned at the start. [Rules] 1. The agent can only move orthogonally (up, down, left, right). 2. The agent MUST visit the numbered yellow cells in strictly increasing numerical order (1, then 2, then 3, etc.). 3. The agent must reach the red end point only after all numbered cells have been visited in order. [Task] Generate a video tracking the orange agent as it visits the numbers sequentially and heads to the final goal. The animation must reflect the shortest valid path for each sequential segment. | |
| Sliding Puzzle | [Scenario] The image displays a sliding tile puzzle grid. The tiles are numbered, and there is exactly one blank space. [Rules] 1. Only tiles orthogonally adjacent to the blank space can be moved. 2. Only slide one tile per move into the blank space. 3. The goal state requires tiles to be arranged in sequential order (top to bottom, left to right), with the blank space at the bottom-right corner. [Task] Generate a video showing the completion of this sliding puzzle. Animate the exact sequence of n moves required to reach the goal state without any extra moves. Keep the camera view fixed. |
Video Diffusion Models
Video diffusion models generate or edit temporally coherent video by iteratively denoising latent sequences conditioned on text, images, motion, or other signals.
See all 812 papers