LIBERO-Pro2.0: Robotik-Foundation-Modelle verlieren 26,5 Punkte, wenn sich Bedingungen ändern (HUST, Tsinghua)

Abstract

LIBERO has emerged as a widely adopted benchmark for evaluating robotic manipulation policies. However, strong performance on LIBERO does not necessarily indicate robust embodied capabilities, as models may exploit benchmark-specific regularities rather than generalize to diverse operating conditions. In this work, we introduce LIBERO-Pro2.0, a comprehensive benchmark for systematically evaluating the robustness of embodied foundation models under distribution shifts. LIBERO-Pro2.0 encompasses 22 static perturbations and 20 runtime interventions across six dimensions: Condition, Environment, Observation, Execution, Robot State Configuration, and Language, yielding 1,648 validated shifted task instances. To support robustness-oriented learning, we further collect 39,390 training trajectories through model-generated and human demonstrations. All shifted task instances undergo six rounds of iterative human review and correction to ensure physical plausibility and task validity. We evaluate 17 representative robot policies spanning vision-language-action models, world-action models, and robustness-oriented policies. Our results reveal substantial robustness gaps across all evaluated paradigms: under runtime distribution shifts, the evaluated models exhibit an average performance drop of 26.5 percentage points, with individual drops reaching 32.5 points. These findings highlight the gap between nominal benchmark performance and robustness under distribution shifts, underscoring the need for systematic robustness evaluation of embodied foundation models.

Webpage | GitHub | Hugging Face | Leaderboard | Community

1 Introduction

Reliable evaluation is essential for measuring progress in embodied intelligence (Yu et al., 2020; James et al., 2020; Mees et al., 2022; Gu et al., 2023; Mu et al., 2025; Zhang et al., 2025). LIBERO has emerged as a de facto standard for tabletop manipulation (Liu et al., 2023), with increasingly many systems approaching saturated performance under its standard protocol (Kim et al., 2025b; Black et al., 2025; Kim et al., 2025a; Qu et al., 2025; Lee et al., 2025; Fang et al., 2026). Yet a fundamental question remains: do these high success rates reflect generalizable embodied capabilities, or merely strong performance within a familiar training–evaluation distribution?

To examine this question, we revisit high-performing systems on LIBERO and observe three striking failure patterns under simple task variations: (1) when the target object is replaced or even removed, models still execute the original grasping behavior; (2) when the task instruction is replaced with meaningless tokens, models continue to produce nearly identical action trajectories; and (3) when the target object is moved away from its familiar position, models still move toward the location commonly seen during training. These qualitative observations motivate a systematic evaluation of sensitivity to task-relevant visual, linguistic, and spatial changes, but do not by themselves establish memorization as the underlying failure mechanism.

These failures expose a broader limitation of current evaluation protocols. Standard benchmarks largely test whether a policy can reproduce successful behavior under conditions close to those seen during training (Yu et al., 2020; James et al., 2020; Mees et al., 2022; Gu et al., 2023; Liu et al., 2023), while deployment requires the same system to remain effective when the scene changes before execution, when unexpected events occur during interaction (Li et al., 2024; Fei et al., 2026; Zhang et al., 2026), and when an initial action fails. Consequently, nominal task success alone does not characterize robustness when operating conditions change. A meaningful evaluation protocol should therefore separate training from evaluation distributions and explicitly test both generalization to static shifts and adaptation to runtime interventions.

To this end, we introduce LIBERO-Pro2.0, a large-scale robustness benchmark for embodied foundation models under static distribution shifts and runtime interventions. LIBERO-Pro2.0 defines 42 perturbation types (22 static and 20 runtime), yielding 1,648 perturbed task variants. These perturbations span scene and object configurations, visual observations, camera settings, robot states, among others. We reserve 8 comprehensively perturbed tasks for evaluation and release the remaining perturbations for training, collecting 39,390 training trajectories. Each perturbed task undergoes six rounds of human verification to ensure validity and reproducibility. We evaluate 17 representative policies spanning vision-language-action models, world-action models, and robustness-oriented policies. Results reveal substantial robustness degradation under both static and runtime distribution shifts, with runtime shifts causing an average performance drop of 26.5 percentage points. Moreover, robustness varies substantially across perturbation types. High nominal success does not guarantee small robustness losses or preservation of policy rankings under distribution shifts. Our main contributions are threefold:

• We introduce LIBERO-Pro2.0, a large-scale robustness benchmark for embodied foundation models, extending LIBERO beyond nominal task success to systematically evaluate robustness under both static distribution shifts and runtime interventions.
• We develop a comprehensive perturbation suite with 42 perturbation types, yielding 1,648 perturbed task variants and 39,390 training trajectories across diverse environments, observations, instructions, robot states, and execution conditions, with rigorous human verification.
• We conduct a large-scale evaluation of 17 representative policies across different model paradigms, revealing substantial robustness degradation under both static and runtime shifts and showing that nominal LIBERO performance does not consistently reflect robustness.

2 Preliminaries

2.1 Embodied Manipulation Tasks

We consider a language-conditioned manipulation task \mathcal{T}=(\ell,e,\mathcal{G}), where \ell is the task instruction, e specifies the environment configuration, and \mathcal{G} is the task-success predicate. Starting from an initial state s_{0}, a policy \pi interacts with the environment for a finite episode horizon T_{\mathrm{ep}}, receiving an observation o_{t} and producing an action a_{t}\sim\pi(\cdot\mid o_{t},\ell_{t}) at each step. The instruction input satisfies \ell_{t}=\ell by default; D20 permits semantics-preserving restatements during execution without changing the task objective or success predicate. The resulting trajectory is \tau=(s_{0},a_{0},\ldots,s_{T_{\mathrm{ep}}}), and an episode is successful if \mathcal{G}(\tau)=1.

2.2 Evaluation under Distribution Shifts

The original LIBERO evaluation distribution closely resembles its training distribution. In real-world deployment, however, operating conditions can deviate substantially from those encountered during training, making the original evaluation insufficient for assessing policy generalization. We therefore introduce controlled distribution shifts into the LIBERO evaluation setting. Given the original evaluation distribution \mathcal{D}_{\mathrm{eval}}, an evaluation transformation \phi parameterized by \eta induces a shifted distribution \mathcal{D}_{\mathrm{eval}}^{\phi}=\phi(\mathcal{D}_{\mathrm{eval}};\eta), while preserving the task objective and success criterion. Performance under \mathcal{D}_{\mathrm{eval}}^{\phi} measures policy generalization when evaluation conditions deviate from those represented during training.

2.3 Static Shifts and Runtime Interventions

We distinguish two types of evaluation transformations according to their temporal behavior during an episode. A static shift \phi_{S} is configured before policy execution, yielding \mathcal{T}^{S}=\phi_{S}(\mathcal{T};\eta). Its intervention parameters or fault rules remain fixed throughout the episod. In contrast, a runtime intervention \phi^{D} is applied during policy execution, with its occurrence and configuration determined by the interaction history \tau_{0:t}, i.e., \phi^{D}(\mathcal{T};t,\tau_{0:t},\eta). Static shifts evaluate generalization under shifted but stationary conditions, whereas runtime interventions evaluate policy robustness to changes that arise during interaction.

3 LIBERO-Pro2.0

LIBERO-Pro2.0 extends LIBERO with robustness evaluation under relevant variations in environments, observations, robot states, execution processes, and task instructions, while preserving task validity and feasibility. An overview of LIBERO-Pro2.0 and its evaluation dimensions is shown in Fig. 3.

3.1 Systematic Distribution Shift Design

We consider two forms of distribution shift according to when the operating condition changes: Static Distribution Shifts and Runtime Distribution Shifts.Static shifts are configured before execution, with intervention parameters or fault rules held fixed throughout an episode, while runtime shifts occur during task execution and alter the environment, observation, robot state, or execution process. The former evaluates out-of-distribution generalization, while the latter evaluates online adaptation and recovery.

Static distribution shifts.

Static distribution shifts characterize changes that are established before execution and remain stationary throughout an episode. Let \phi^{S}\in\Phi^{S} denote a static shift operator and \eta its configuration. Applying \phi^{S} to a nominal task \mathcal{T} induces a shifted task \mathcal{T}^{S}=\phi^{S}(\mathcal{T};\eta), where \eta is specified before the rollout and held fixed throughout execution. LIBERO-Pro2.0 instantiates 22 static distribution shifts over the task environment, observation process, robot configuration, and language condition, covering object configuration and appearance, scene composition, camera and observation conditions, robot initialization and calibration, temporal configuration, and instruction expression. These shifts reflect deployment-relevant variations that arise in real-world robotic manipulation, making robustness to such out-of-distribution conditions essential for deployment.

Runtime distribution shifts.

Runtime distribution shifts characterize changes that emerge after task execution has begun. Let \phi^{D}\in\Phi^{D} denote a runtime shift operator and \eta its configuration. Each shift is associated with a trigger function g_{\phi}(\tau_{0:t}) defined over the interaction trajectory \tau_{0:t}; the trigger determines when the shift is introduced, while \eta specifies its realization and temporal extent. LIBERO-Pro2.0 instantiates 20 runtime distribution shifts over the task environment, observation process, robot and action execution, and language condition, covering object or receiver relocation, dynamic occlusion and obstacles, camera and observation failures, frame-stream and synchronization anomalies, transient latency, action-execution disruptions, robot-state changes, semantics-preserving instruction restatements, and recoverable execution failures. These shifts capture execution-time changes that can occur during real-world deployment, where a robust policy must continuously adapt its behavior and recover from unexpected deviations to maintain stable task execution.

3.2 Data Collection

LIBERO-Pro2.0 is built from the 40 tasks in LIBERO-Goal, LIBERO-Spatial, LIBERO-Object, and LIBERO-10. Using random seed 142, we sample two tasks from each suite for held-out evaluation, yielding 8 evaluation tasks and 32 training tasks. After applying all applicable distribution shifts and filtering invalid task–shift combinations, the training and evaluation sets contain 1,313 and 335 valid instances, respectively, for a total of 1,648 validated shifted task instances. For robustness-oriented learning, we collect 30 trajectories for each training instance, yielding 39,390 trajectories from \pi_{0.5}, GPT-5.6 Sol with Codex, and human demonstrations. All authors conduct six rounds of iterative human review and correction over all 1,648 distribution-shift instances. In each round, every instance is executed twice using \pi_{0.5}, producing approximately 3,296 rollout videos per round and 19,776 reviewed rollouts across six rounds, totaling more than 82 hours of footage. Reviewers verify that each shift is correctly realized and that tasks remain semantically valid and physically executable, including spatial consistency after relocation, valid occlusions or obstacles, feasible execution paths, and correct runtime triggering. Temporal and action-stream shifts are additionally checked against execution logs when necessary. Invalid or ambiguous instances are corrected and re-evaluated, while task–shift combinations that fail validation are removed.

4 Experiments

4.1 Experimental Setup

We evaluate 17 representative robot manipulation policies spanning different policy paradigms, using their official checkpoints and inference settings. Experiments are conducted on the 8 held-out tasks of LIBERO-Pro2.0 under nominal execution, 22 static shifts, and 20 runtime shifts. Additional experimental details are provided in Appendix C. Our evaluation is organized around the following research questions:

• Overall Performance Landscape: How robust are current robot policies under diverse static and runtime distribution shifts?
• RQ1: What limits robustness under runtime distribution shifts?
• RQ2: Does robustness compose under compound distribution shifts?
• RQ3: Can robustness be learned from limited demonstrations and transferred to held-out tasks?

4.2 Overall Performance Landscape

Finding 1: High nominal performance does not imply strong robustness.

Table 1 and Table 2 show that, despite nominal success rates ranging from 63.8% to 98.5%, all policies degrade substantially under distribution shifts. Static shifts reduce average success rates to 33.9%–71.2% (25.1–41.8 points drop), while runtime shifts reduce them to 35.3%–81.8% (16.7–32.5 points drop). Moreover, robustness rankings do not consistently follow nominal performance. For example, FastWAM achieves higher nominal performance (97.8%) than \pi_{0.5} (93.3%), but its runtime robustness decreases to 70.1%, lower than \pi_{0.5} (73.8%). This ranking reversal indicates that nominal task success does not necessarily predict robustness under runtime distribution shifts. Therefore, robustness evaluation reveals additional capabilities beyond standard task solving metrics.

Finding 2: Static evaluation does not fully characterize runtime robustness. Figure 5 compares semantically matched static–runtime perturbation pairs, including object relocation, goal relocation, path obstruction, occlusion, camera changes, and language variation. Despite similar perturbation mechanisms, their effects differ across static and runtime settings. For example, averaged across the four suites, LingBot-VA achieves 56.7% success under static receiver-pose changes (S02), compared with 29.2% under runtime receiver-pose updates (D02). Camera changes exhibit the opposite pattern: 6.3% under S15 versus 60.8% under D07. These contrasting patterns show that static evaluation alone does not fully characterize runtime robustness.

Finding 3: Different perturbation categories expose heterogeneous robustness bottlenecks.

Robustness varies substantially across perturbation dimensions. Language variations remain relatively easy, with all models achieving over 46% success under S21, whereas execution-related shifts are considerably more challenging, reducing OpenVLA-OFT and \pi_{0} to 0.0% and 5.0% under S20. Runtime shifts further expose distinct weaknesses in observation, execution, and physical-state adaptation, showing that robustness is inherently multidimensional.

4.3 RQ1: What Limits Robustness under Runtime Distribution Shifts?

We investigate why policies fail under runtime distribution shifts through three controlled interventions targeting feedback utilization, closed-loop update frequency, and post-perturbation recovery.

RQ1-A: Can Policies Use Updated Observations?

We examine whether policies can exploit observations updated after runtime perturbations. Under live feedback, the policy continuously receives post-perturbation visual observations, whereas under freeze feedback, it repeatedly receives the last observation before the perturbation and therefore does not receive updated visual observations. Here, S_{1} denotes the success rate under a dynamic perturbation, while S_{0} denotes the success rate under the corresponding no-perturbation condition. Therefore, S_{1,\mathrm{live}} and S_{1,\mathrm{freeze}} measure performance with and without access to updated observations after a perturbation, whereas S_{0,\mathrm{live}} and S_{0,\mathrm{freeze}} capture the normal feedback effect in the absence of perturbations. We define

G_{\mathrm{feedback}}=(S_{1,\mathrm{live}}-S_{1,\mathrm{freeze}})-(S_{0,\mathrm{live}}-S_{0,\mathrm{freeze}}),

where positive values indicate a larger live-versus-freeze benefit under perturbation than in the corresponding no-perturbation condition. Table 3 summarizes the results, with complete results in Appendix A.2. (1) Reduced feedback benefit under perturbations. Negative values indicate that the benefit of updated visual observations is smaller than under nominal execution, not that updated observations provide no benefit. For example, under D01, OpenVLA-OFT achieves 5.4% success with live observations and 0.0% with frozen observations, despite G_{\mathrm{feedback}}=-46.1 percentage points. (2) Feedback benefit depends on perturbation type. Although most category-level contrasts are negative, \pi_{0.5} and Cosmos Policy obtain positive average contrasts of 7.5 and 1.1 percentage points, respectively, on robot-state changes (D17–D19).

RQ1-B: Does Closed-Loop Update Frequency Limit Robustness?

We study whether action chunking delays the use of updated observations by fixing the prediction horizon H and varying the number of executed actions K before re-observation. Detailed horizon settings are shown in Appendix C.5. We evaluate target replanning (D01), goal replanning (D02), feasibility replanning (D03), path replanning (D05), and recovery replanning (D18) under execution ratios K/H. Figure 6 presents the results. (1) Replanning frequency exhibits a non-monotonic effect. Average success increases from 21.6\% at K/H=1 to 24.1\% at 1/2, but drops to 19.2\% at 1/8, showing that more frequent re-observation does not uniformly improve robustness. (2) Frequency sensitivity is policy-dependent. FastWAM and Cosmos Policy benefit more from shorter execution intervals, whereas Anchor-Align performs better with longer horizons. OpenVLA-OFT remains weak across settings, indicating that update frequency alone cannot compensate for limited perturbation handling.

RQ1-C: How Do Interventions Affect Recovery after a Runtime Shift?

We compare three recovery interventions following runtime shifts: Hold pauses execution, Retry replays actions from an unperturbed reference trajectory, and Reset restores the robot to its pre-perturbation pose. The baseline, Continue, proceeds under the perturbed condition without an additional recovery intervention. For each intervention I, we report the success-rate change \Delta_{I}=S_{I}-S_{\mathrm{continue}} in percentage points. Table 4 summarizes the average effects, with per-perturbation results in Appendix A.3. (1) Hold has policy-dependent effects. Hold increases average success by 18.9–28.1 percentage points for four of the five policies, but decreases it by 15.7 points for OpenVLA-OFT. (2) Retry reduces success on average. Retry lowers average success by 16.8–40.8 percentage points across all five policies, although it improves performance under some individual perturbations. (3) Reset has small average effects for most policies. The average change ranges from -0.4 to +2.5 percentage points for \pi_{0.5}, Anchor-Align, FastWAM, and Cosmos Policy, whereas OpenVLA-OFT declines by 31.6 points.

4.4 RQ2: Does Robustness Compose?

Real-world perturbations often occur jointly, raising the question of whether robustness to individual shifts transfers to compound settings. For a model m and perturbation composition \mathcal{C}=\{c_{1},\dots,c_{k}\}, we define the weakest-single gap as \Delta_{m}(\mathcal{C})=p_{m}(\mathcal{C})-\min_{c_{i}\in\mathcal{C}}p_{m}(c_{i}). A negative value indicates lower success than the weakest constituent perturbation; it does not by itself establish an interaction effect beyond independent failure accumulation. Figure 7 summarizes these gaps, while Appendix A.4 reports detailed success rates.

Robustness to individual perturbations does not reliably compose.

Table 5 shows that P02 (S09+S13), P06 (S09+D13), and T03 (S09+S22+D13) reduce success to only 9.2\%–12.9\%, although their constituent perturbations remain individually manageable (69.6\%–99.2\%). Thus, robustness to isolated shifts can collapse when multiple assumptions are violated jointly.

Recovery capability is also non-compositional.

As shown in Appendix A.4, \pi_{0.5} performs well on D02, D18, and D20 individually, yet drops to 22.9\% on P08 (D02+D18) and 17.5\% on P10 (D18+D20). This indicates that recovery from one runtime disturbance does not guarantee recovery under concurrent shifts.

4.5 RQ3: Can Robustness Be Learned and Generalized?

We ask whether robustness can be learned from limited demonstrations and transferred to tasks held out from additional fine-tuning. We train \pi_{0.5} on eight training tasks with ten trajectories per task, while keeping all evaluation tasks disjoint. We consider five semantically matched static–dynamic perturbation families: S01/D01 (object pose), S02/D02 (receiver pose), S05/D05 (path obstacle), S15/D07 (camera calibration), and S17/D19 (robot state). Training details are provided in Appendix C.6.

Robustness can be learned from limited demonstrations.

After robustness-oriented fine-tuning, our model achieves 70.1\% average robustness on unseen tasks, outperforming existing policies (28.0\%–47.9\%) in Table 6. The largest gain appears on path changes (S05/D05), where our model reaches 96.3\%, compared with below 20\% for all baselines.

Generalization depends on perturbation semantics.

Learned robustness transfers well in receiver pose (73.2\%) and robot-state shifts (91.7\%), but remains limited under camera calibration shifts (20.8\%). This suggests robustness generalizes better when perturbation semantics preserve stable task constraints than when they require broader perception–action recalibration.

5 Related Work

Embodied Foundation Models. Recent advances in large-scale robot datasets and foundation models have significantly improved the generalization capabilities of robotic manipulation policies. Datasets such as Open X-Embodiment and DROID provide diverse demonstrations across tasks, environments, and robotic platforms (Open X-Embodiment Collaboration et al., 2023; Khazatsky et al., 2024). Building on these resources, vision-language-action (VLA) models, including OpenVLA, \pi_{0}, and OpenVLA-OFT, learn generalizable visuomotor policies from large-scale multimodal data (Kim et al., 2025b; Black et al., 2025; Kim et al., 2025a). More recently, world-action models such as Cosmos Policy, LingBot-VA, and FastWAM have explored predictive world representations to support action generation and visuomotor control (Kim et al., 2026; Li et al., 2026; Yuan et al., 2026).

Robot Manipulation Benchmarks and Robustness Evaluation. Existing benchmarks, including Meta-World, RLBench, CALVIN, ManiSkill2, and LIBERO, provide standardized protocols for evaluating multi-task and language-conditioned robotic manipulation (Yu et al., 2020; James et al., 2020; Mees et al., 2022; Gu et al., 2023; Liu et al., 2023). Recent benchmarks such as RoboCasa, RoboTwin, and VLABench further expand task complexity and scene diversity (Nasiriany et al., 2024; Mu et al., 2025; Zhang et al., 2025), while RoboDojo introduces a unified simulation-and-real-world evaluation framework covering diverse manipulation capabilities (Chen et al., 2026). Beyond nominal task success, recent studies investigate policy robustness through environmental variations, domain randomization, and controlled perturbations (Li et al., 2024; Chen et al., 2025; Zhang et al., 2026). In particular, LIBERO-PRO exposes the reliance of VLA models on memorized behaviors under changes in objects, initial states, instructions, and environments (Zhou et al., 2025), while LIBERO-Plus evaluates robustness under progressively challenging static distribution shifts (Fei et al., 2026). Despite these advances, existing benchmarks primarily emphasize task diversity or robustness to pre-execution variations, leaving adaptation to disturbances arising during execution insufficiently evaluated. LIBERO-Pro2.0 addresses this critical gap by systematically assessing both static generalization and runtime robustness within a unified benchmark.

6 Conclusion

We present LIBERO-Pro2.0, a systematic benchmark for evaluating the robustness of embodied foundation models under static distribution shifts and runtime interventions. Our evaluation reveals substantial robustness gaps that remain hidden by strong nominal performance, while further analyses highlight challenges in online adaptation, recovery, compound robustness, and robustness transfer. We hope LIBERO-Pro2.0 provides a practical foundation for developing embodied policies that remain reliable under diverse and evolving deployment conditions.

References

1. Bjorck et al. (2025) J. Bjorck, F. Castañeda, N. Cherniadev, X. Da, R. Ding, L. Fan, Y. Fang, D. Fox, F. Hu, S. Huang, et al. Gr00t n1: an open foundation model for generalist humanoid robots. arXiv preprint arXiv:2503.14734.
2. Black et al. (2025) K. Black, N. Brown, D. Driess, A. Esmail, M. R. Equi, C. Finn, N. Fusai, L. Groom, K. Hausman, B. Ichter, S. Jakubczak, T. Jones, L. Ke, S. Levine, A. Li-Bell, M. Mothukuri, S. Nair, K. Pertsch, L. X. Shi, L. Smith, J. Tanner, Q. Vuong, A. Walling, H. Wang, and U. Zhilinsky \pi_{0}: A vision-language-action flow model for general robot control. In Robotics: Science and Systems,
3. Bu et al. (2025) Q. Bu, Y. Yang, J. Cai, S. Gao, G. Ren, M. Yao, P. Luo, and H. Li Learning to Act Anywhere with Task-centric Latent Actions. In Proceedings of Robotics: Science and Systems, External Links: Document, Link
4. Chen et al. (2026) T. Chen, Y. Chen, Z. Li, J. Tang, K. Su, et al. RoboDojo: a unified sim-and-real benchmark for comprehensive evaluation of generalist robot manipulation policies. arXiv preprint arXiv:2607.04434.
5. Chen et al. (2025) T. Chen, Z. Chen, B. Chen, Z. Cai, Y. Liu, Z. Li, Q. Liang, X. Lin, Y. Ge, Z. Gu, et al. RoboTwin 2.0: a scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation. arXiv preprint arXiv:2506.18088.
6. Dalal et al. (2026) D. Dalal, S. Patel, C. Jain, J. Kim, U. Mishra, A. Baratian, H. Ha, H. Ji, S. Lazebnik, and U. Jain Generalizable vla finetuning via representation anchoring and language-action alignment. arXiv preprint arXiv:2607.13429.
7. Fang et al. (2026) H. Fang, J. Duan, D. Clay, S. Wang, S. Liu, W. Huang, X. Fan, W. Tsai, S. Chen, Y. R. Wang, S. Xing, J. Cho, J. S. Park, A. Eftekhar, P. Sushko, K. Farley, A. Wadhwa, C. Harrison, W. Han, Y. Lee, E. VanderBilt, R. Hendrix, S. Ellawela, L. Ngoo, J. Chai, Z. Ren, A. Farhadi, D. Fox, and R. Krishna MolmoAct2: action reasoning models for real-world deployment. arXiv preprint arXiv:2605.02881.
8. Fei et al. (2026) S. Fei, S. Wang, J. Shi, Z. Dai, J. Cai, P. Qian, L. Ji, X. He, S. Zhang, Z. Fei, J. Fu, J. Gong, and X. Qiu LIBERO-plus: a progressive robustness benchmark for visual-language-action models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 38574–38583.
9. Gu et al. (2023) J. Gu, F. Xiang, X. Li, Z. Ling, X. Liu, T. Mu, Y. Tang, S. Tao, X. Wei, Y. Yao, X. Yuan, P. Xie, Z. Huang, R. Chen, and H. Su ManiSkill2: a unified benchmark for generalizable manipulation skills. In International Conference on Learning Representations,
10. James et al. (2020) S. James, Z. Ma, D. Rovick Arrojo, and A. J. Davison RLBench: the robot learning benchmark & learning environment. IEEE Robotics and Automation Letters.
11. Khazatsky et al. (2024) A. Khazatsky, K. Pertsch, S. Nair, A. Balakrishna, S. Dasari, S. Karamcheti, S. Nasiriany, M. K. Srirama, L. Y. Chen, K. Ellis, et al. DROID: a large-scale in-the-wild robot manipulation dataset. In Proceedings of Robotics: Science and Systems,
12. Kim et al. (2025a) M. J. Kim, C. Finn, and P. Liang Fine-tuning vision-language-action models: optimizing speed and success. arXiv preprint arXiv:2502.19645.
13. Kim et al. (2026) M. J. Kim, Y. Gao, T. Lin, Y. Lin, Y. Ge, G. Lam, P. Liang, S. Song, M. Liu, C. Finn, and J. Gu Cosmos policy: fine-tuning video models for visuomotor control and planning. In International Conference on Learning Representations,
14. Kim et al. (2025b) M. J. Kim, K. Pertsch, S. Karamcheti, T. Xiao, A. Balakrishna, S. Nair, R. Rafailov, E. P. Foster, P. R. Sanketi, Q. Vuong, T. Kollar, B. Burchfiel, R. Tedrake, D. Sadigh, S. Levine, P. Liang, and C. Finn OpenVLA: an open-source vision-language-action model. In Proceedings of the 8th Conference on Robot Learning, Vol. 270, pp. 2679–2713.
15. Lee et al. (2025) J. Lee, J. Duan, H. Fang, Y. Deng, S. Liu, B. Li, B. Fang, J. Zhang, Y. R. Wang, S. Lee, W. Han, W. Pumacay, A. Wu, R. Hendrix, K. Farley, E. VanderBilt, A. Farhadi, D. Fox, and R. Krishna MolmoAct: action reasoning models that can reason in space. arXiv preprint arXiv:2508.07917.
16. Li et al. (2026) L. Li, Q. Zhang, Y. Luo, S. Yang, R. Wang, F. Han, M. Yu, Z. Gao, N. Xue, X. Zhu, Y. Shen, and Y. Xu Causal world modeling for robot control. arXiv preprint arXiv:2601.21998.
17. Li et al. (2024) X. Li, K. Hsu, J. Gu, K. Pertsch, O. Mees, H. R. Walke, C. Fu, I. Lunawat, I. Sieh, S. Kirmani, S. Levine, J. Wu, C. Finn, H. Su, Q. Vuong, and T. Xiao Evaluating real-world robot manipulation policies in simulation. arXiv preprint arXiv:2405.05941.
18. Liu et al. (2023) B. Liu, Y. Zhu, C. Gao, Y. Feng, Q. Liu, Y. Zhu, and P. Stone LIBERO: benchmarking knowledge transfer for lifelong robot learning. In Advances in Neural Information Processing Systems, Vol. 36.
19. Mees et al. (2022) O. Mees, L. Hermann, E. Rosete-Beas, and W. Burgard CALVIN: a benchmark for language-conditioned policy learning for long-horizon robot manipulation tasks. IEEE Robotics and Automation Letters 7 (3), pp. 7327–7334.
20. Mu et al. (2025) Y. Mu, T. Chen, Z. Chen, S. Peng, Z. Lan, Z. Gao, Z. Liang, Q. Yu, Y. Zou, M. Xu, L. Lin, Z. Xie, M. Ding, and P. Luo RoboTwin: dual-arm robot benchmark with generative digital twins. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 27649–27660.
21. Nasiriany et al. (2024) S. Nasiriany, A. Maddukuri, L. Zhang, A. Parikh, A. Lo, A. Joshi, A. Mandlekar, and Y. Zhu RoboCasa: large-scale simulation of everyday tasks for generalist robots. In Robotics: Science and Systems,
22. Open X-Embodiment Collaboration et al. (2023) Open X-Embodiment Collaboration, A. O’Neill, A. Rehman, A. Gupta, A. Maddukuri, A. Gupta, A. Padalkar, A. Lee, A. Pooley, A. Gupta, et al. Open x-embodiment: robotic learning datasets and rt-x models. arXiv preprint arXiv:2310.08864.
23. Pertsch et al. (2025) K. Pertsch, K. Stachowicz, B. Ichter, D. Driess, S. Nair, Q. Vuong, O. Mees, C. Finn, and S. Levine FAST: Efficient Action Tokenization for Vision-Language-Action Models. In Proceedings of Robotics: Science and Systems, External Links: Document, Link
24. Physical Intelligence et al. (2025) Physical Intelligence, K. Black, N. Brown, J. Darpinian, K. Dhabalia, D. Driess, A. Esmail, M. Equi, C. Finn, N. Fusai, et al. \pi_{0.5}: A vision-language-action model with open-world generalization. arXiv preprint arXiv:2504.16054.
25. Qu et al. (2025) D. Qu, H. Song, Q. Chen, Y. Yao, X. Ye, Y. Ding, Z. Wang, J. Gu, B. Zhao, D. Wang, and X. Li SpatialVLA: exploring spatial representations for visual-language-action model. arXiv preprint arXiv:2501.15830.
26. Tan et al. (2025) S. Tan, K. Dou, Y. Zhao, and P. Krähenbühl Interactive post-training for vision-language-action models. arXiv preprint arXiv:2505.17016.
27. Yu et al. (2020) T. Yu, D. Quillen, Z. He, R. Julian, K. Hausman, C. Finn, and S. Levine Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning. In Proceedings of the Conference on Robot Learning, pp. 1094–1100.
28. Yuan et al. (2026) T. Yuan, Z. Dong, Y. Liu, and H. Zhao Fast-wam: do world action models need test-time future imagination?. arXiv preprint arXiv:2603.16666.
29. Zhang et al. (2025) S. Zhang, Z. Xu, P. Liu, X. Yu, Y. Li, Q. Gao, Z. Fei, Z. Yin, Z. Wu, Y. Jiang, and X. Qiu VLABench: a large-scale benchmark for language-conditioned robotics manipulation with long-horizon reasoning tasks. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 11142–11152.
30. Zhang et al. (2026) Z. Zhang, Z. Li, B. Rahmati, R. H. Yang, Y. Ma, A. Rasouli, S. Pakdamansavoji, Y. Wu, L. Zhang, T. Cao, F. Wen, X. Wang, X. Quan, and Y. Zhang Do world action models generalize better than vlas? a robustness study. arXiv preprint arXiv:2603.22078.
31. Zheng et al. (2025) J. Zheng, J. Li, Z. Wang, D. Liu, X. Kang, Y. Feng, Y. Zheng, J. Zou, Y. Chen, J. Zeng, Y. Zhang, J. Pang, J. Liu, T. Wang, and X. Zhan X-vla: soft-prompted transformer as scalable cross-embodiment vision-language-action model. arXiv preprint arXiv:2510.10274.
32. Zhou et al. (2025) X. Zhou, Y. Xu, G. Tie, Y. Chen, G. Zhang, D. Chu, P. Zhou, and L. Sun LIBERO-pro: towards robust and fair evaluation of vision-language-action models beyond memorization. arXiv preprint arXiv:2510.03827.

Appendix A Additional Experimental Results

This appendix provides the complete LIBERO-Pro2.0 results supplementing the feedback-utilization, recovery-intervention, and robustness-composition analyses in the main paper.

A.1 Main Results