Expand-and-Prune: Test-Time Candidate-Space Adaptation for End-to-End Autonomous Driving

Fabian Schmidt; Karol Fedurko; Markus Enzweiler; Abhinav Valada

cs.ROOct 16, 2026

Expand-and-Prune: Test-Time Candidate-Space Adaptation for End-to-End Autonomous Driving

Authors: Fabian Schmidt, Karol Fedurko, Markus Enzweiler, Abhinav Valada

Organizations: Esslingen University of Applied Sciences · University of Freiburg

Abstract

Candidate-based end-to-end driving planners reason over a finite set of trajectory hypotheses. However, for sparse planners, a limited candidate set may provide insufficient support for scene-relevant maneuvers, while fixed downstream candidate budgets do not account for prediction uncertainty. To address these challenges, we introduce Expand-and-Prune, a test-time framework that jointly adapts candidate support and capacity without updating learned parameters. The framework expands the native candidate set using semantic driving intent and temporally propagated predictions and then uses uncertainty in intermediate trajectory scores to adaptively prune the resulting candidates. Across four heterogeneous candidate-based planners and four benchmarks, Expand-and-Prune consistently improves planning performance. It achieves state-of-the-art results on LangAuto, increasing the Driving Score from 68.2 to 75.9, while providing further improvement on Bench2Drive, Fail2Drive, and NAVSIMv2, with particularly strong improvements in out-of-distribution scenarios. Moreover, in its full instantiation, 72.5% of selected trajectories originate from the newly introduced intent-guided or temporal candidates, confirming that candidate-space expansion provides useful hypotheses beyond those generated natively by the planner. The code is available at https://github.com/iis-esslingen/Expand-and-Prune.

Figures & tables

Figure 1: Concept and performance of Expand-and-Prune . Intent-guided and temporal candidates expand the planner-native candidate set, while adaptive pruning regulates downstream capacity. On LangAuto, Expand-and-Prune improves LAD-Drive from $68.2$ to $75.9$ Driving Score, achieving SOTA performance.

Figure 2: Overview of Expand-and-Prune . Planner-native candidates are augmented with intent-guided and temporal candidates, processed by the frozen planner, and adaptively pruned based on intermediate scores before further refinement. The backbone denotes the upstream perception and context-encoding components, including vision encoders and, where applicable, language-based modules, while planner stages denote candidate-processing modules such as scoring or trajectory refinement. Dashed boxes indicate optional modules.

Figure 3: LAD-Drive action-specific trajectory prototype banks.

Planner	Method	Intent	Temporal	Pruning
LAD-Drive [ 22 ]	Sparse diffusion	✓	✓	✓
BridgeDrive [ 19 ]	Sparse diffusion	–	✓	✓
DriveSuprim [ 34 ]	Dense selection	–	–	✓
SparseDriveV2 [ 27 ]	Dense selection	–	–	✓

Table 1: Planner-specific instantiations of Expand-and-Prune .

Method	Venue	Tiny			Short			Long			Mean
		DS $\uparrow$	RC $\uparrow$	IS $\uparrow$	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$
DSDrive [ 20 ]	arXiv’25	60.7	72.5	0.84	62.1	76.2	0.81	29.6	39.3	0.77	50.8	62.7	0.81
LMDrive [ 23 ]	CVPR’24	66.5	77.9	0.85	50.6	60.0	0.84	36.2	46.6	0.81	51.1	61.5	0.83
AD-H [ 40 ]	arXiv’24	77.5	85.1	0.91	56.1	68.0	0.78	44.0	53.2	0.83	59.2	68.8	0.84
BEVDriver [ 29 ]	IROS’25	70.2	81.3	0.87	66.7	77.8	0.87	48.9	59.7	0.82	61.9	72.9	0.85
SToRM [ 12 ]	ICRA’26	78.8	86.9	0.92	64.5	74.7	0.88	44.2	56.8	0.82	62.5	72.8	0.87

Table 2: Closed-loop performance on LangAuto. Best results are highlighted in bold.

Table 3: Component ablation on LangAuto. The selected configuration (gray) of each stage is propagated to the subsequent stage.

Figure 4: Qualitative comparison on LangAuto. Each pair compares LAD-Drive (left) with LAD-Drive + Expand-and-Prune (right). Trajectory color encodes confidence from white (low) to red (high). The first scenario shows a guardrail collision during a left turn avoided through improved candidate coverage. In the latter two, route deviations are mitigated by better alignment with the planner’s intent belief.

Table 4: Transfer of Expand-and-Prune across planners and benchmarks. (a) BridgeDrive on Bench2Drive and Fail2Drive, where HM denotes the harmonic mean of Driving Score and Success Rate. (b) Adaptive pruning on DriveSuprim and SparseDriveV2 on NAVSIMv2.

Figure 5: Provenance of trajectories across route-length categories.

Method	Head [ms] $\downarrow$	Total [ms] $\downarrow$
LAD-Drive	6.0	45.0
+ Intent	8.4	47.5
+ Intent + Temporal	9.2	48.5
+ Intent + Temporal + Pruning	8.2	47.2
BridgeDrive	73.4	95.3
+ Temporal + Pruning	73.1	94.9

Table 5: Runtime on an NVIDIA L40S GPU. Head latency denotes the planner-specific candidate-processing stages.

	Candidates		Tiny			Short			Long			Mean
Allocation	Native	Intent Budget	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$
–	20	0	83.50	87.00	0.95	71.30	78.10	0.89	49.80	58.30	0.86	68.20	74.47	0.90
Prob.	20	10	84.92	87.63	0.96	74.89	81.06	0.90	53.43	62.56	0.86	71.08	77.08	0.91
	20	20	81.20	82.06	0.98	70.16	77.63	0.89	57.37	66.38	0.87	69.58	75.36	0.91
	20	30	81.09	85.17	0.95	76.82	83.14	0.88	58.51	70.18	0.83	72.14	79.50	0.89
	20	40	78.83	82.16	0.96	74.79	80.41	0.93	60.23	68.73	0.88	71.28	77.10	0.92

Table 6: Extended ablation of intent-guided candidate expansion on LangAuto. Prob. denotes probabilistic allocation according to the action belief, while WTA uses only the most probable action. Entropy

(a,b)

denotes an adaptive intent budget bounded by

a

and

b

. Gray denotes the selected configuration; best mean results are bold.

Temporal Memory		Tiny			Short			Long			Mean
Strategy	Setting	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$
None	–	81.09	85.17	0.95	76.82	83.14	0.88	58.51	70.18	0.83	72.14	79.50	0.89
Top- $K$	$1$	82.34	83.83	0.98	77.41	81.30	0.94	58.27	65.61	0.89	72.67	76.91	0.94
	$3$	83.98	86.95	0.96	75.46	83.99	0.91	59.58	68.52	0.87	73.01	79.82	0.91
	$5$	85.93	79.58	0.95	73.37	77.11	0.95	56.98	65.70	0.88	72.09	74.13	0.93
Entropy	$(1,3)$	83.12	85.89	0.97	69.96	77.81	0.89	59.68	67.46	0.88	70.92	77.05	0.91

Table 7: Extended ablation of temporal-memory selection on LangAuto. All variants use the selected intent-guided expansion with

20

native and

30

intent-guided candidates. For entropy-based selection,

(K_{\min},K_{\max})

denotes the adaptive memory bounds and

\tau=0.5

. Gray denotes the selected configuration; best mean results are bold.

Memory	Pruning		Tiny			Short			Long			Mean
	Strategy	Setting	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$	DS $\uparrow$	RC $\uparrow$	IS $\uparrow$
Entropy $(1,5)$	None	–	82.40	87.16	0.94	75.85	84.61	0.89	61.90	71.05	0.88	73.39	80.94	0.90
Entropy $(1,5)$	Top- $K$	$1$	65.25	69.51	0.91	63.86	71.64	0.89	40.66	48.32	0.80	56.59	63.16	0.87
		$3$	86.57	87.85	0.98	72.63	78.96	0.89	53.67	60.19	0.89	70.95	75.67	0.92
		$5$	83.20	85.57	0.97	80.97	87.91	0.89	57.60	65.66	0.88	73.92	79.72	0.92
		$10$	84.75	86.76	0.97	76.44	81.55	0.92	57.96	65.20	0.89	73.05	77.84	0.92

Table 8: Extended ablation of adaptive pruning on LangAuto. All variants use

20

native and

30

intent-guided candidates. Unless stated otherwise, temporal memory uses entropy-adaptive selection with bounds

(1,5)

. Entropy-based memory and pruning use

\tau=0.5

. Gray denotes the selected configuration; best mean results are bold. The final row reports the matched fixed-capacity configuration.

Method	EPDMS $\uparrow$	NC $\uparrow$	DAC $\uparrow$	DDC $\uparrow$	TLC $\uparrow$	EP $\uparrow$	TTC $\uparrow$	LK $\uparrow$	HC $\uparrow$	EC $\uparrow$
DriveSuprim (ResNet-34)	83.069	0.975	0.965	0.994	0.996	0.863	0.966	0.955	0.983	0.749
+ Adaptive Pruning	83.664	0.981	0.975	0.995	0.997	0.861	0.973	0.952	0.983	0.743
DriveSuprim (ViT-L)	87.033	0.984	0.986	0.996	0.998	0.904	0.978	0.970	0.983	0.766
+ Adaptive Pruning	87.264	0.988	0.990	0.996	0.998	0.892	0.982	0.966	0.983	0.775
SparseDriveV2	87.040	0.985	0.982	0.996	0.998	0.904	0.979	0.972	0.983	0.781
+ Adaptive Pruning	87.368	0.989	0.983	0.997	0.999	0.887	0.984	0.969	0.983	0.806

Table 9: Extended NAVSIMv2 metric breakdown for DriveSuprim and SparseDriveV2. NC denotes No-At-Fault Collision, DAC Driveable-Area Compliance, DDC Driving-Direction Compliance, TLC Traffic-Light Compliance, EP Ego Progress, TTC Time to Collision, LK Lane Keeping, HC History Comfort, and EC Two-Frame Extended Comfort. Gray rows denote adaptive pruning. Best results within each baseline–pruning pair are highlighted in bold.

Figure 6: Additional qualitative comparisons on Long routes of LangAuto. For each scenario, the two left columns show LAD-Drive and the two right columns show LAD-Drive + Expand-and-Prune , using a driving view and corresponding bird’s-eye view. Trajectory color encodes confidence from white (low) to red (high). Top: in Scenario 36, LAD-Drive leaves the intended lane and collides with an object, while Expand-and-Prune remains in the correct lane. Middle: in Scenario 37, LAD-Drive drifts out of its lane during a highway merge and collides with a traffic sign, whereas Expand-and-Prune safely completes the merge. Bottom: in Scenario 43, ambiguity around a highway exit leads LAD-Drive into the guardrail, while Expand-and-Prune stabilizes the prediction and continues straight.

Autonomous Driving Planning

Autonomous driving planning selects safe, feasible vehicle actions and trajectories amid traffic, uncertainty, road rules, and changing goals.

See all 382 papers

PrismAD: Decoupled Planning via Semantic Mixture-of-Planners for End-to-End Autonomous Driving
Jul 11, 2026Kang Ding, Zhigui Lin, Hongsong Wang +5End-to-End Autonomous Driving Mixture of Experts
School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China. · State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing 100084, China. · School of Cyberspace Security, Southeast University, Nanjing 210096, China. +3
Test-Time Trajectory Optimization for Autonomous Driving
Jun 5, 2026Yihong Xu, Eloi Zablocki, Yuan Yin +4Trajectory Optimization Trajectory Generation
valeo.ai, Paris, France · Sorbonne Université, CNRS, ISIR, F-75005 Paris, France
SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving
Mar 31, 2026Wenchao Sun, Xuewu Lin, Keyu Chen +4Autonomous Driving Planning End-to-End Autonomous Driving
Tsinghua University, Beijing, China · Horizon Continental Technology, Beijing, China · Horizon, Beijing, China

Jul 11, 2026J/K move · Enter open · S save

PrismAD: Decoupled Planning via Semantic Mixture-of-Planners for End-to-End Autonomous Driving

Kang Ding, Zhigui Lin, Hongsong Wang, Jie Gui+4

School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China. · State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing 100084, China. · School of Cyberspace Security, Southeast University, Nanjing 210096, China.+3

End-to-End Autonomous Driving Mixture of Experts Autonomous Driving Planning

Open paper AskPDF arXiv

This letter presents PrismAD, a decoupled end-to-end autonomous driving framework based on a Semantic Mixture-of-Planners. Existing planners usually aggregate heterogeneous scene tokens into a coupled representation space, forcing a single planning branch to jointly model agent interaction, road geometry, and driving intention. Such coupling may weaken factor-specific reasoning and obscure the contribution of different planning cues. To address this limitation, PrismAD partitions scene tokens into interaction, geometry, and intent groups, and assigns them to independent planning experts with the same architecture but separate parameters. Each expert learns a specialized motion-planning representation, while a semantics-aware router adaptively aggregates expert predictions with separate routing weights for motion prediction and ego planning. Sparse top-

K

activation with noisy gating is further introduced to improve routing robustness and reduce unnecessary expert computation. Extensive experiments on the nuScenes open-loop dataset and NeuroNCAP closed-loop benchmark demonstrate that PrismAD exhibits competitive performance. Our code will be released soon.

Abstract

Autonomous Driving Planning

Explore similar work

PrismAD: Decoupled Planning via Semantic Mixture-of-Planners for End-to-End Autonomous Driving

Test-Time Trajectory Optimization for Autonomous Driving

SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving