- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The authors notice that current interactive world models are likely to overlook physical interactions between carriers and the surrounding environments, which leads to a implausible motion though with high quality. To address this problem, they proposed CarPhy, an agentic pose-correction framework that improves the physical plausibility of camera motion in interactive world models. Given recent visual observations, camera poses, carrier specifications, and the user’s intended motion, CarPhy constructs a physical scene and applys verification loop checks the trajectory for contact plausibility, pose consistency, and alignment with the motion intent, prompting further refinement or abstention when necessary. Experiments on a curated benchmark of 187 samples demonstrate improved physical-event recognition and pitch-response timing across multiple model backbones.
Critical strengths
-
The topic is well-motivated; as generative world models often struggle to account for physical constraints during video generation, leading to implausible motion. The authors take advantage of an agent to interpret visual observations while the physics engine computes the carrier’s response to the intended motion. The combination allows semantic understanding to inform simulation, offering a practical approach to improving physical plausibility
-
The paper is clearly written and well organized, with figures that effectively illustrate the proposed agentic framework and tables that clearly present its performance gains over the baselines.
Critical weaknesses
-
The contribution of this work is limited; CarPhy primarily uses an agent’s semantic and commonsense reasoning to interpret and refine scene assets, while established physics tools compute the carrier’s trajectory. As the framework builds on an existing coding-agent harness, its contribution appears to lie mainly in task-specific integration and workflow design.
-
The concerns about verification. Passing verification does not guarantee that the scene has been correctly interpreted. For example, misclassifying a rigid obstacle as traversable vegetation and disabling its collision could allow a trajectory based on incorrect physical assumptions to pass verification. Although scene edits are constrained, the verifier cannot independently establish the correctness of the underlying semantic interpretation
-
Constraining the carrier trajectory alone does not guarantee physical consistency in the generated video. The video generator may alter obstacle geometry, height, or contact relationships, so a trajectory that is feasible in the reconstructed scene may not remain consistent with the generated environment.
-
Current experiments is mainly done through a curated dataset containing 187 samples and only 8 samples are blocked motion. The primary fine-grained metric measures the time at which the pitch angle first reaches specified thresholds. This provides a limited assessment of full-trajectory accuracy, contact dynamics, and physical responses during turning or continuous interaction.
Questions for authors
The proposed method relies on an iterative agent loop for scene refinement, trajectory simulation, and verification, which may introduce substantial computational overhead and latency. Reporting end-to-end latency and computational cost, alongside the average number of agent iterations and simulation calls, would help assess its practicality for interactive world modeling.
5 comments
Response to Reviewer 1Heb (2/3)
Q3. Does constraining the carrier trajectory guarantee physical consistency in the generated video?
Constraining the carrier trajectory alone does not guarantee physical consistency in the generated video. The video generator may alter obstacle geometry, height, or contact relationships, so a trajectory that is feasible in the reconstructed scene may not remain consistent with the generated environment.
A3. Thank you for highlighting the connection between trajectory correction and video consistency. Within our scope of short- to medium-duration interactions, CarPhy's trajectory correction improves the physical consistency of generated videos. Figure 8 demonstrates consecutive corrections over 8–10 seconds, and our additional benchmark experiments confirm the benefits of trajectory correction on both video generators.
We identified two concurrent benchmarks addressing related physical interactions, WorldExam [2] and WorldRoamBench [1]. At the time of evaluation, WorldRoamBench had released its test cases but not its evaluation code, while WorldExam’s test suite and evaluation code were unavailable. We therefore select 20 wall-interaction and 9 uphill/downhill cases from WorldRoamBench and reimplement its Clipping and Terrain Following evaluation protocols.
We report the generated-video results in Section 4.8 and Table 7 (Page 10 of the revised manuscript). The evaluation setup and protocol reimplementation are detailed in Appendix M (Page 30).
Table 3. Generated-video physical evaluation on selected WorldRoamBench cases.
| Generator | Pose condition | Clipping score ↑ | Terrain Following score ↑ |
|---|---|---|---|
| Lyra 2.0 | Without correction | 35.0 | 22.2 |
| Lyra 2.0 | With CarPhy | 75.0 | 66.7 |
| LingBot World 2.0 | Without correction | 15.0 | 11.1 |
| LingBot World 2.0 | With CarPhy | 75.0 | 55.6 |
Note. Terrain Following evaluates uphill/downhill behavior, corresponding to the PU/PD events studied in our work [1]. Both scores use our reimplementation of WorldRoamBench's evaluation protocols [1].
With paired inputs, seeds, and generation budgets, CarPhy increases Clipping scores from 35.0 to 75.0 on Lyra 2.0 and from 15.0 to 75.0 on LingBot World 2.0. Terrain Following scores rise from 22.2 to 66.7 and 11.1 to 55.6, respectively (Table 3). These results show that correcting the carrier trajectory reduces wall pass-through and improves terrain following in the final generated videos.
Code. Our WorldRoamBench evaluation code is available through the anonymous link provided in Appendix M (Page 30 of the revised manuscript).
Q4. Can the authors expand the evaluation beyond pitch-event timing to assess full-trajectory accuracy, contact dynamics, and physical responses during turning or continuous interaction, with more blocked-motion cases?
Current experiments is mainly done through a curated dataset containing 187 samples and only 8 samples are blocked motion. The primary fine-grained metric measures the time at which the pitch angle first reaches specified thresholds. This provides a limited assessment of full-trajectory accuracy, contact dynamics, and physical responses during turning or continuous interaction.
A4. We appreciate your suggestions for a more comprehensive evaluation. We have expanded the evaluation to more complex scenarios from an interactive world model benchmark and reported full-trajectory position and rotation errors. The results show that CarPhy improves physical responses in generated videos, reducing wall pass-through and improving terrain following.
We evaluate 20 wall-interaction cases, including turning motions, and 9 uphill/downhill cases from WorldRoamBench [1], using our reimplementation of its evaluation protocols. CarPhy increases Clipping scores from 35.0 to 75.0 on Lyra 2.0 and from 15.0 to 75.0 on LingBot World 2.0. Terrain Following scores improve from 22.2 to 66.7 and 11.1 to 55.6, respectively (Table 4). For continuous interaction, Figure 8 demonstrates 8–10 seconds of generation through 4–5 consecutive correction windows.
Response to Reviewer 1Heb (3/3)
Table 4. Generated-video physical evaluation on WorldRoamBench cases, including turning motions (20 wall-interaction and 9 uphill/downhill cases, 0–100 scale).
| Generator | Pose condition | Clipping score ↑ | Terrain Following score ↑ |
|---|---|---|---|
| Lyra 2.0 | Without correction | 35.0 | 22.2 |
| Lyra 2.0 | With CarPhy | 75.0 | 66.7 |
| LingBot World 2.0 | Without correction | 15.0 | 11.1 |
| LingBot World 2.0 | With CarPhy | 75.0 | 55.6 |
Note. Both scores use our reimplementation of WorldRoamBench’s evaluation protocols [1]. Terrain Following evaluates uphill/downhill behavior, corresponding to the PU/PD events studied in our work [1].
The trajectory results also show why pointwise pose errors alone do not reliably measure the effectiveness of physical correction. Raw intent achieves the lowest position and rotation errors (Table 5), yet produces worse physical behavior in the generated videos. Figure 14 in Appendix K (Page 28) shows how differences in response timing and magnitude can produce large pointwise errors despite a physically meaningful correction.
We have included the trajectory results and supporting visualizations in Appendix K (Pages 27–28 of the revised manuscript).
Table 5. Full-trajectory position and rotation errors.
| Method | Position RMSE (m) ↓ | Mean rotation error (deg) ↓ |
|---|---|---|
| Raw intent | 0.463 | 5.42 |
| Host only | 0.939 | 11.03 |
| One-shot repair | 0.801 | 8.35 |
| Full CarPhy | 0.869 | 9.19 |
Note. Errors are averaged over the trajectories each method returns on the PU/PD/NA cases. Rotation error is the mean angular difference from ground truth at matched timestamps.
Q5. What are the latency, computational cost, average iterations, and simulation calls?
The proposed method relies on an iterative agent loop for scene refinement, trajectory simulation, and verification, which may introduce substantial computational overhead and latency. Reporting end-to-end latency and computational cost, alongside the average number of agent iterations and simulation calls, would help assess its practicality for interactive world modeling.
A5. Thank you for asking about the computational cost and latency. Full CarPhy takes 250.2 s per run, averaging 3.67 agent iterations, 3.67 model calls, and 2.75 simulator calls, with 74.3k recorded input and output tokens per run (Table 6). We also evaluate a variant in which the agent explicitly orchestrates the recurring modeling and execution steps consolidated into the host.
Notably, this latency does not preclude CarPhy’s use as a data simulator in downstream workflows that interleave pose correction with IWM generation, where high-quality video generation is prioritized over low latency.. Compared with this variant, Full CarPhy reduces model calls from 8.67 to 3.67 and runtime from 532.4 s to 250.2 s, illustrating the efficiency gained by consolidating recurring operations. These times start from cached reconstructed observations. The initial reconstruction and segmentation add about 6 s per run. At this cost, CarPhy does not yet support real-time updates for two-second interaction windows.
We have included the cost measurements and experimental setup in Appendix O (Page 31 of the revised manuscript).
Table 6. Computation cost.
| Method | Time per run (s) | Agent iterations | Model calls | Simulator calls | Recorded tokens per run (k) |
|---|---|---|---|---|---|
| Host only | 41.2 | 0.00 | 0.00 | 1.67 | 0.0 |
| One-shot repair | 146.2 | 1.46 | 1.38 | 2.46 | 16.9 |
| CarPhy with agent-orchestrated execution | 532.4 | 8.67 | 8.67 | 3.21 | 96.8 |
| Full CarPhy | 250.2 | 3.67 | 3.67 | 2.75 | 74.3 |
Note. Means cover all 24 attempts per method, starting from cached reconstructed observations. Tokens sum recorded input and output usage.
References
[1] Xu et al. WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models. arXiv:2606.31672, 2026.
[2] Yang et al. WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity. arXiv:2608.02603, 2026.
Response to Reviewer 1Heb (1/3)
We thank you for recognizing the motivation and clarity of the work! We clarify the task-specific contribution and address verification, downstream consistency, and practical cost.
Q1. Is the contribution mainly integration on an existing coding-agent harness?
A1. Thank you for the opportunity to clarify our contribution. CarPhy’s contribution goes beyond integrating tools into an existing coding-agent harness. Even with access to the same tools, a general coding-agent harness struggles to solve this task. Therefore, our contribution is to identify camera-carrier physics as a missing component in interactive world models and design an agent and its orchestration to address it.
First, a general coding-agent harness cannot effectively solve this task through tool access alone. Pi Full Tools achieves 43.8% Macro-F1, compared with 67.5% for CarPhy (see Table 1 below). This gap shows the importance of designing how the agent interprets the scene, models carrier–environment interactions, and uses simulation feedback.
Second, our host already provides a substantial part of the solution. It implements the physical modeling procedure we developed for this task and achieves 66.0% Macro-F1. Its performance demonstrates the contribution of CarPhy’s modeling design, which is absent from the general coding-agent harness.
Third, the agent adds flexibility through scene-dependent decisions and iterative refinement. It can revise physical interpretations that the default host procedure leaves unresolved, such as distinguishing traversable vegetation from rigid obstacles. Full CarPhy improves Macro-F1 to 67.5%, while a single repair achieves 63.2%, supporting the value of feedback-guided iteration over an isolated edit.
We report these comparisons in Section 4.7 (Pages 9–10) and Table 6 (Page 10) of the revised manuscript, with further details in Appendix I (Page 26).
Table 1. Overall comparison and component ablations of CarPhy (Kimi-K3, PU/PD/NA).
Q2. The concerns about verification. How reliable is CarPhy’s verification when an incorrect scene interpretation can still produce a trajectory that passes physical checks?
A2. Thank you for raising this concern about semantic verification. CarPhy’s verification extends beyond the deterministic pose verifier. It combines semantic checks during scene repair with physical checks during simulation. And we also find that this combined verification process is reliable in practice, with 94.7% of accepted semantic repairs judged correct in our human audit.
For the human audit, we manually assessed all 19 accepted agent repairs against the original visual observations and checked whether incorrect repairs passed physical verification. 18 repairs were correct, and the failure raised by the reviewer occurred in one case, where a shadow on flat ground was misinterpreted as a slope (Table 2).
We have included the audit procedure, results, and failure case in Appendix N (Page 30 of the revised manuscript).
Table 2. Reliability of semantic repairs.