- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
VarioDrive proposes a planning-oriented post-training framework that couples driving-scene descriptions and intent reasoning with autoregressive trajectory prediction. Time-indexed position and heading tokens receive geometry-aware soft supervision, while decomposed reinforcement-learning rewards assess visual grounding, reasoning-to-trajectory alignment, and preference-dependent planning. Adaptive inference uses one plan for simpler scenes and compares safety-, efficiency-, and comfort-oriented candidates in more complex scenes. Reported performance reaches 92.42 PDMS on NAVSIM with Slow selection and a driving score of 79.70 on Bench2Drive.
Critical strengths
- Planning-oriented post-training addresses a meaningful reasoning-to-action gap. Separating scene descriptions, driving rationales, and waypoint answers exposes intermediate outputs for targeted feedback. Such a formulation helps study whether language reasoning supports physical planning.
- Geometry-aware waypoint supervision provides a concrete improvement. Time-indexed pose tokens preserve spatial structure, while nearby bins receive graded targets instead of identical penalties. Adding geometric soft supervision improves PDMS from 71.93 to 80.96 under a matched tokenization setting.
- Preference-conditioned planning produces useful candidate diversity. Safety, efficiency, and comfort conditions yield different progress and motion characteristics. With three candidates per pool, mixed-preference oracle PDMS reaches 93.26 versus 91.67 for the strongest single-preference pool.
- Evaluation spans complementary autonomous-driving benchmarks. NAVSIM, nuScenes, and Bench2Drive measure non-reactive planning, maneuver-level decisions, and closed-loop driving. Results provide a broader perspective than a single benchmark score.
- Ablations support several components of the training and inference pipeline. Stage-decomposed rewards increase NAVSIM PDMS from 88.75 to 90.84 over answer-only reinforcement learning. Learned selection also improves over random selection on an identical candidate pool.
Critical weaknesses
- Reasoning rewards do not establish factual or causal faithfulness. Rewarding a higher likelihood of the generated trajectory after conditioning on a rationale may also favor incorrect but predictive explanations. Removing the reasoning prefix changes the input distribution, so stronger counterfactual reasoning tests are needed.
- Synthesized rationales may encourage post-hoc explanations. Training rationales are generated with access to a motion summary derived from the expert trajectory. Consequently, models may learn to justify known actions rather than independently derive better decisions from observations.
- Novelty relative to closely related reasoning-aware driving methods is not sufficiently isolated. Existing approaches already optimize reasoning-action consistency and trajectory quality, whereas matched comparisons mainly examine answer-only feedback and selected VLA recipes. Comparisons against similar process-reward designs under aligned training settings would clarify the methodological contribution.
- Adaptive routing lacks matched-compute controls. Slow inference is triggered on 56.22% of scenes, but comparable random, uncertainty-based, or oracle routing policies are not evaluated. Without such controls, improvements cannot be confidently attributed to learning when additional reasoning is useful.
- Inference latency substantially limits practical deployment. Complete-output latency is 2.87 seconds for Fast, 7.15 seconds for Slow, and 5.30 seconds for Adaptive on an H800 at batch size eight. Single-scene response times and delay-aware closed-loop safety have not been established.
- Closed-loop advantages are modest and inconsistent across outcomes. Driving score reaches 79.70 versus 78.84 for AutoVLA, but success rate falls to 55.91% versus 57.73%, with lower reported comfort. Reliance on published external baseline results also limits the strength of cross-method conclusions.
Questions for authors
- Can authors evaluate semantically contradictory but length-matched reasoning traces to distinguish causal planning support from token-likelihood gains?
- How would the stage-decomposed reward compare with existing reasoning-action alignment objectives under the same backbone, data, and compute?
- What are the results of random, uncertainty-based, and oracle Fast/Slow routing at the same Slow-call budget?
- Can authors report single-scene end-to-end latency and latency-aware closed-loop driving outcomes?
- How do authors explain lower closed-loop success and comfort than AutoVLA, and can external baselines be matched more closely?
6 comments
Response 2 - Expert-future-conditioned SFT rationales (W2)
W2. Synthesized rationales may encourage post-hoc explanations. Training rationales are generated with access to a motion summary derived from the expert trajectory. Consequently, models may learn to justify known actions rather than independently derive better decisions from observations.
We agree that SFT rationales explain the demonstrated action, and we use them to teach the output format and the link between observations and decisions. The expert motion summary is given only to the annotation model, never to the policy: in both SFT and RL, the policy conditions on observations and driving context, and during RL its thinking is rewarded for supporting its own generated trajectory rather than the expert's. Consistently, when the turn command is replaced with go straight, the generated reasoning changes accordingly in 79/80 scenes, as illustrated in appendix B.3.
Concretely, during on-policy RL rollouts, the policy receives observations and driving context without the expert future trajectory, and generates the rationale followed by its own trajectory. The thinking reward evaluates the rationale's likelihood support for that generated trajectory. Expert references used to compute trajectory-quality rewards are training supervision, not future information supplied to the policy.
Thus, SFT provides demonstration-based reasoning supervision, while RL optimizes reasoning–trajectory alignment on the policy's own outputs. Table 6's thinking-reward ablation supports its planning utility. The contribution is on-policy alignment rather than a guarantee that every rationale faithfully exposes the model's internal decision process.
Response 3 - Comparison with existing process/alignment rewards (W3 & Q2)
W3. Novelty relative to closely related reasoning-aware driving methods is not sufficiently isolated. Existing approaches already optimize reasoning-action consistency and trajectory quality, whereas matched comparisons mainly examine answer-only feedback and selected VLA recipes. Comparisons against similar process-reward designs under aligned training settings would clarify the methodological contribution.
Q2. How would the stage-decomposed reward compare with existing reasoning-action alignment objectives under the same backbone, data, and compute?
On the same 750 policy outputs, our thinking reward gives the highest paired preference for the original thinking over the counterfactual one (99.33%, vs. 95.33% for entropy reduction and 83.67% for Alpamayo-R1-style reasoning–action consistency) and the fewest ties (1.33%). This compares reward signals rather than retrained policies. Table 2 separately compares VarioDrive and the AlphaDrive training recipe on the same Qwen3-VL backbone (87.14% vs. 78.50% nuScenes accuracy). Full stage-reward RFT adds 2.09 PDMS over answer-only RFT (Table 10).
Stepwise process verifiers such as ThinkPRM assess intermediate correctness. Our stage-decomposed feedback evaluates scene grounding, intent–trajectory alignment, and preference-dependent trajectory quality. The rewards are combined into a completion-level advantage. The intent component measures the likelihood gain of the same generated trajectory and uses the paper's discrete reward .
We compare scoring functions on 750 shared pairs without further training, replacing only a key judgment and its action conclusion within thinking. Valid-token entropy reduction measures . The reasoning–action consistency baseline follows the meta-action matching principle used by Alpamayo-R1.
For pairs, we report:
\qquad T=\frac{1}{N}\sum_i\mathbf{1}(R_i^{\mathrm{orig}}=R_i^{\mathrm{swap}}).$$ | Scoring method | $100W$ | $100T$ | | --- | ---: | ---: | | Our discrete thinking reward | 99.33 | 1.33 | | Valid-token entropy reduction | 95.33 | 5.60 | | Reasoning–action consistency | 83.67 | 12.93 | Our reward gives the highest paired preference and lowest tie rate. This compares scoring behavior on shared policy outputs. It does not retrain the policy under alternative rewards. Existing controlled training ablations provide complementary evidence: thinking feedback raises nuScenes accuracy from 80.95% to 85.92%, while full stage-reward RFT improves NAVSIM PDMS from 88.75 to 90.84 over answer-only RFT (Tables 6 and 10).Response 4 - Random, uncertainty, and oracle routing (W4 & Q3)
W4. Adaptive routing lacks matched-compute controls. Slow inference is triggered on 56.22% of scenes, but comparable random, uncertainty-based, or oracle routing policies are not evaluated. Without such controls, improvements cannot be confidently attributed to learning when additional reasoning is useful.
Q3. What are the results of random, uncertainty-based, and oracle Fast/Slow routing at the same Slow-call budget?
At the same Slow budget (50% of 2,048 stratified NAVTEST scenes), learned routing reaches 90.63 PDMS, outperforming random routing (89.76) and uncertainty-based routing (89.52). We did not evaluate Oracle-K. The detailed results are provided as follows.
We evaluate a stratified subset of 2,048 NAVTEST scenes, with 1,024 scenes predicted as simple and 1,024 predicted as complex by the model. Random-K, Uncertainty-K, and learned routing each assign exactly 1,024 scenes to Slow, using the same Fast/Slow predictions.
| Policy | Slow calls (%) | PDMS | NC | DAC | TTC |
|---|---|---|---|---|---|
| Always Fast | 0 | 88.59 | 98.40 | 97.67 | 96.90 |
| Always Slow | 100 | 91.15 | 99.18 | 97.94 | 97.37 |
| Random-K | 50 | 89.76 | 98.82 | 97.73 | 96.91 |
| Uncertainty-K | 50 | 89.52 | 98.73 | 97.65 | 96.89 |
| Learned routing | 50 | 90.63 | 98.98 | 97.88 | 97.24 |
Random-K is a single random assignment. Uncertainty-K routing ranks scenes by the normalized predictive entropy of the Fast answer. Learned routing improves PDMS by 0.87 over Random-K and by 1.11 over Uncertainty-K. The expected PDMS for uniform random assignment, calculated from the reported Fast/Slow means, is 89.87, giving a 0.76-point advantage for learned routing.
Response 5 - Single-scene latency and latency-aware closed-loop outcomes (W5 & Q4)
W5. Inference latency substantially limits practical deployment. Complete-output latency is 2.87 seconds for Fast, 7.15 seconds for Slow, and 5.30 seconds for Adaptive on an H800 at batch size eight. Single-scene response times and delay-aware closed-loop safety have not been established.
Q4. Can authors report single-scene end-to-end latency and latency-aware closed-loop driving outcomes?
Single-scene latency (one H200, batch size 1, 200 scenes) is 3.15 s for Fast and 8.14 s for Slow on average (P95: 3.425 s and 8.832 s). We agree that this is far from real-time deployment. Our Bench2Drive results use the standard synchronous protocol, in which the simulator waits for each plan, so they do not measure the effect of delay.
We add per-scene planning measurements on 200 scenes in BF16, with one H200 per request and scene batch size 1. Eight independent workers each use one GPU; Slow batches its three candidates within the same scene and then performs model selection. Timing includes image loading, preprocessing, and complete structured-output generation, including selection, but excludes model loading, PDMS evaluation, and the controller. Table 15 reports complete-output latency on one H800 at batch size 8.
| Mode | Scenes | Mean (s) | P50 (s) | P95 (s) |
|---|---|---|---|---|
| Fast | 200 | 3.153 | 3.167 | 3.425 |
| Slow | 200 | 8.137 | 8.151 | 8.832 |
For context, AutoVLA's Table 2 reports mean runtimes of 1.072 s for trajectory-only Fast thinking and 10.518 s for CoT-based Slow thinking. In VarioDrive, Fast already generates structured reasoning and Slow compares three preference-conditioned plans. These published values provide context. They are not measurements under a shared hardware and timing protocol.
Our Bench2Drive results follow the standard synchronous loop, which waits for the agent before advancing simulation time. They therefore evaluate planning under that protocol. The new measurements resolve the missing single-scene timing information. Evaluating the effect of execution delay on closed-loop behavior requires a separate delay-aware execution protocol.
We thank the reviewer for the detailed comments, and for recognizing the planning-oriented formulation, the geometric waypoint supervision, and the preference-conditioned candidate diversity. We added counterfactual reasoning tests, routing controls with the same number of Slow calls, and single-scene latency measurements, and will include them in the revised paper. In summary:
Response 1 - Contradictory, length-matched reasoning (W1 & Q1)
We conducted this test on 750 NAVTEST scenes. Replacing one decision-relevant judgment in the thinking with another scene’s justification and action conclusion, while holding observations, navigation, description, and format fixed, lowers the PDMS of the regenerated trajectories from 91.81 to 35.89. The paired preference rate for the original thinking is 99.33% with half credit for ties, compared with 95.33% for entropy reduction and 83.67% for reasoning–action consistency, and copying the action statement into the thinking did not increase the reward in any tested pair. Both the reward and the planner therefore respond to the decision content of the reasoning under this intervention.
Paired preference is (nwin+0.5ntie)/750, with ties also reported separately. Length matching preserves the qualitative result. Because the intervention changes the action conclusion as well as its justification, this measures decision-semantic sensitivity rather than factual correctness with the action held fixed.
On 750 randomly sampled NAVTEST scenes using safety-first Fast inference, original trajectories score 91.82 PDMS on this subset, compared with 90.84 on full NAVTEST (Table 4). Regeneration with the original thinking gives 91.81, versus 35.89 after intervention, a 55.92-point decrease.