Generative video models are increasingly used as visual world simulators, yet their primary strength lies in rendering plausible pixels rather than reasoning about how a world should evolve. Coherent world evolution requires more than visual fidelity: when an event occurs, a model must infer its consequences for the entities in the world and then render the resulting state. For example, after a wild beast appears, the model should not only depict the wild beast, but also infer whether a nearby person should flee, take cover, or fight back based on the realized scene. Existing diffusion-based video models lack an explicit mechanism for maintaining world state and reasoning over such event-conditioned consequences, often producing visually plausible but behaviorally static or causally inconsistent outputs. To make this reasoning gap concrete and measurable, we propose a new problem, Out-of-Sight Causal Evolution, which requires a model to render an event, reason about its consequences for the evolving world state, and reveal a causally plausible outcome as the world continues to evolve, even out of sight. As a baseline reference solution, we introduce EvoWorld, a brain-renderer collaboration framework in which a vision-language model serves as the world brain: it observes generated segments, maintains an evolving account of the world, and reasons about plausible state transitions, while a segment-autoregressive video renderer realizes them visually. We further introduce EvoWorld-Data and EvoWorld-Bench for training and evaluating event realization, causal reactions, and revisit consistency. Experiments show that EvoWorld substantially improves event-conditioned causal evolution over recent models while preserving visual quality and consistency, establishing a reference point for reasoning-guided, autonomous world evolution beyond the current field of view.
Figures & tables
Figure 1: Challenges in Out-of-Sight Causal Evolution . The camera first observes a subject (a vendor and his handcart), moves away to reveal a newly requested event (a collapsing building facade), and then moves back to the original scene. Previous methods (rows 1–4) exhibit various failures. In contrast, EvoWorld (row 5) realizes the event, revisits the original subject, and renders a causally plausible reaction while preserving subject and scene consistency.
Figure 2: Overview of the data engine for EvoWorld. Structured scenarios are rendered into single-take out-of-sight interactions, verified against visual evidence, temporally annotated, and converted into a training supervision dataset and evaluation benchmark.
Figure 3: Examples and statistics of EvoWorld-Data and EvoWorld-Bench. The upper part illustrates representative training and benchmark examples, while the lower part summarizes their scale and scenario diversity.
Figure 4: Overview of the EvoWorld framework. (a) Stage 1 learns out-of-sight reactive rendering. (b) Stage 2 refines the renderer through online autoregressive adaptation. (c) Inference uses brain–renderer collaboration for Out-of-Sight Causal Evolution .
Task metrics
Visual quality, consistency, and motion
Method
Core
Revisit
Event
Causal
React.
Visual
Subj. Cons.
Bg. Cons.
Motion
LingBot-World ( Team et al., 2026b )
15.8
92.5
77.5
29.2
31.3
68.8
87.6
94.6
98.0
LingBot-World-v2 ( Gao et al., 2026 )
20.0
76.7
68.3
27.1
25.4
76.7
82.6
92.5
98.4
YUME-1.5 ( Mao et al., 2026 )
15.8
62.5
86.7
22.5
20.0
65.4
72.9
88.7
99.0
SANA-WM ( Zhu et al., 2026 )
13.3
88.3
67.5
26.7
24.2
53.8
67.7
90.8
98.7
Echo-WM ( Zhang et al., 2026b )
16.7
60.8
66.7
22.5
21.7
82.9
97.6
89.2
98.7
Table 1: Comparison results (%) on the EvoWorld-Bench. Best results are shown in bold and second-best results are underlined. Core denotes the proportion of cases concurrently achieving successful revisit, event realization, and full causal plausibility.
Figure 6Figure 7
Appendix figures & tables5 assets
Supplementary material from the paper’s appendix.
Appendix
Split
Videos
Events
Scenes
Reactions
/ cases
Fam.
Types
Fam.
Types
Fam.
Types
EvoWorld-Data
12k
19
65
16
63
5
14
EvoWorld-Bench
120
17
55
16
56
–
–
Appendix
Table 5: Reviewed semantic coverage of EvoWorld-Data and EvoWorld-Bench. Reaction categories are reported only for the training data; EvoWorld-Bench does not define target reactions.
Table 6: Training and inference settings for EvoWorld. Stage 2 inherits the Stage-1 LoRA architecture and IAA configuration.
Figure 7: Case study summarizing the VLM brain’s observation, event-conditioned reasoning, prompt generation, and verification over an out-of-sight rollout.
Task metrics
Visual quality, consistency, and motion
Method
Core
Revisit
Event
Causal
React.
Visual
Subj. Cons.
Bg. Cons.
Motion
Wan2.2 TI2V-5B ( Wan et al., 2025 )
8.3
40.0
87.5
17.1
18.3
77.9
81.7
95.4
98.8
LTX-2.3 ( HaCohen et al., 2026 )
27.5
97.5
94.2
43.3
42.1
88.8
96.7
99.2
99.2
LTX-2.5 ( HaCohen et al., 2026 )
34.2
95.0
90.8
50.8
42.9
90.4
95.8
98.8
99.4
EvoWorld (ours; autoregressive)
90.8
100.0
97.5
94.2
85.0
83.8
99.2
98.3
99.5
Appendix
Table 7: One-shot general video generators on EvoWorld-Bench, with EvoWorld included as an autoregressive reference below the separator. Best results among the one-shot models are bold (%).
Method
Core
Revisit
Event
Causal
React.
MiniMax-H3 ( MiniMax, 2026 )
21.7
100.0
99.2
44.2
47.9
EvoWorld (ours; autoregressive)
90.8
100.0
97.5
94.2
85.0
Appendix
Table 8: Task metrics of one-shot MiniMax-H3 on EvoWorld-Bench.