cs.ROOct 23, 2026
SaveDo VLAs Know They Will Fail? Interpretable Success and Failure Patterns in Physical AI Systems
Organizations: Kahlert School of Computing, University of Utah
Abstract
Vision-Language-Action (VLA) models have emerged as powerful general-purpose robot policies, but their successes and failures remain difficult to diagnose and understand. In this work, we show that sparse autoencoder (SAE) representations of OpenVLA activations contain outcome-predictive information and can be used to predict task failure before the robot reaches an unrecoverable state. Moreover, to provide insights into what common behaviors may contribute to these outcomes, we identify individual SAE features whose strong activations are associated with specific stages of success or failure, and uncover recurring behavioral patterns by localizing temporal intervals where these features exhibit significant activation changes. We further develop a VLM-based interpretation pipeline to generate behavioral descriptions of these patterns and validate their correspondence to feature activations on held-out intervals.
Figures & tables
Figure 1: For late timesteps, almost all trajectories are failures, so low performance is most relevant. (a) Raw activations and SAE features outperform the majority baseline at early timesteps. (b) Both representations achieve above-chance AUROC, indicating that they retain outcome-predictive information. (c) For held-out failures aligned at their point of no return (PNR, red line), predicted failure probability rises as estimated recoverability declines.
| False alarms | Actionable | Lead | |
|---|---|---|---|
| 0.5 | 0.64 | 0.88 | 190 |
| 0.7 | 0.25 | 0.55 | 160 |
| 0.9 | 0.14 | 0.33 | 70 |
Table 1: Alarms relative to the point of no return (held-out). False alarms: fraction of successful trajectories that raise an alarm. Actionable: fraction of failures alarmed before their PNR. Lead: median steps from alarm to PNR for actionable alarms.
| Feature | Success rate | Automatically inferred pattern | AUROC | |
| 480 | 3.33% | In Task 9 , arm moves right from the stove toward the moka pot handle without holding the pot | 0.72 | 0.26 |
| 467 | 3.33% | In Task 1 , gripper hovers close to the moka pot handle without moving the pot | 0.84 | 0.22 |
| 850 | 3.33% | In Task 1 , open gripper approaching the not-yet-grasped middle moka pot | 0.42 | 0.53 |
| 1578 | 93.33% | In Task 4 , carrying the grasped task object left toward the basket | 0.89 | 0.04 |
| 1671 | 86.67% | In Task 3 , carrying the grasped green-and-red-label can left and placing it in the basket | 1.00 | 0.17 |
| All 12 feature–task pairs (261 clips; shuffled-description AUROC 0.58) | 0.76 | 0.17 | ||
Table 2: Representative outcome-associated SAE features and their automatically inferred behavioral patterns. Success rates are based on each feature’s top 30 trajectories. AUROC evaluates descriptions on held-out clips; is the difference from shuffled-description AUROC. Task descriptions are provided in Table 3 .
Figure 2: Activation traces over time and automatically detected critical intervals for the failed trajectories with the strongest activations of feature 480 in Task 1: "Put both moka pots on the stove". It shows five uniformly sampled visualization frames above the full activation trace.
Appendix figures & tables5 assets
Supplementary material from the paper’s appendix.
Appendix
| Task | Instruction | Success |
|---|---|---|
| 0 | pick up the book and place it in the back compartment of the caddy | 80% |
| 1 | put both moka pots on the stove | 12% |
| 2 | put both the alphabet soup and the cream cheese box in the basket | 56% |
| 3 | put both the alphabet soup and the tomato sauce in the basket | 54% |
| 4 | put both the cream cheese box and the butter in the basket | 76% |
| 5 | put the black bowl in the bottom drawer of the cabinet and close it | 46% |
Table 3: LIBERO-10 tasks (numbered alphabetically by instruction) and the success rate of OpenVLA over the 50 benchmark initial states.
Figure 3: Temporal activation of success-related feature 1671 on Task 3.
Figure 4: Activation traces over time and automatically detected critical intervals for three failed trajectories with the strongest activations of feature 480 in Task 1. It shows five uniformly sampled visualization frames above the full activation trace.
| Relation | Feature | Success rate | # Unique Tasks | Active trajectories |
|---|---|---|---|---|
| Failure | 480 | 3.33% | 4 | 303 |
| Failure | 850 | 3.33% | 1 | 164 |
| Failure | 35 | 3.33% | 1 | 346 |
| Failure | 467 | 3.33% | 1 | 240 |
| Failure | 685 | 6.67% | 5 | 367 |
| Success | 1578 | 93.33% | 3 | 235 |
Table 4: SAE features with the strongest outcome associations. For each feature, the success rate is computed over the top- trajectories. We show features with the lowest and highest success rates, corresponding to failure- and success-associated features, respectively.
| Relation | Feature | Task | Automatically inferred pattern | Outcome relation | AUROC | |
|---|---|---|---|---|---|---|
| Failure | 35 | 1 | Empty arm swings right into the workspace before touching any object | ordinary task progress | 0.53 | 0.46 |
| Failure | 467 | 1 | Gripper hovers close to the moka pot handle without moving the pot | unclear | 0.84 | 0.22 |
| Failure | 480 | 1 | Stalled, unlifted, or pushing grasp attempt after closing in on the moka pot | early indicator | 0.56 | 0.06 |
| Failure | 480 | 8 | End effector holding or touching the yellow-and-white mug and moving it toward the open microwave | ordinary task progress | 0.65 | 0.15 |
| Failure | 480 | 9 | Arm moves right from the stove toward the moka pot handle / frying pan area without holding the pot | early indicator | 0.72 | 0.26 |
| Failure | 850 | 1 | Open gripper approaching the not-yet-grasped middle moka pot | ordinary task progress | 0.42 | 0.53 |
Table 5: Automatic interpretations of the four highest-ranked failure-related and success-related SAE features and their reproduction-test scores on held-out clips: AUROC of a judge VLM that sees only the description, and the difference to a shuffled description of another feature on the same clips. Each explanation uses the three strongest task-specific critical clips and one independently sampled successful demonstration. The outcome-relation category is produced by the external VLM. Task numbers follow Table 3 .
More in this topic
Vision-Language-Action Models
Vision-language-action models turn visual observations and natural-language instructions into actions for robots and other embodied agents.
See all 1,194 papers