From Proxy Learning to Driving Decisions: A Transfer-Based Framework for Evaluating Future-Aware Autonomous Driving Planners

• URL: http://arxiv.org/abs/2609.02688v1
• Date: Wed, 02 Sep 2026 14:55:14 GMT
• Title: From Proxy Learning to Driving Decisions: A Transfer-Based Framework for Evaluating Future-Aware Autonomous Driving Planners
• Abstract summary: Proxy-to-Decision Transfer Framework evaluates when learned future information supports a reliable driving-performance improvement claim.<n>Decision-Transfer Decomposition Module localizes value loss through score margins, switch-conditioned utility, and support-versus-selection regret.
• Score: 0.34519649635864585
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Future-aware representations and world models are increasingly used in proposal-based autonomous-driving planners to improve trajectory selection. However, improvements in proxy objectives or restricted subsets are often interpreted as planning gains without verifying proposal ordering, selected trajectories, full-scale utility, and critical driving components. We propose the Proxy-to-Decision Transfer (PDT) Framework, an analysis framework that evaluates when learned future information supports a reliable driving-performance improvement claim. Its Decision-Transfer Decomposition Module localizes value loss through score margins, switch-conditioned utility, and support-versus-selection regret. Its Reliability-Constrained Validation Module requires exact pairing, a minimum meaningful effect, scale-expanded confirmation, safety non-compensation, sequential comparability, and family-level robustness. On a representative future-aware planner evaluated with NAVSIM-v1, component BCE decreases from 0.705 to 0.530 while held selected PDM decreases from 0.963 to 0.961. A separate candidate improves a 512-record prefix by 0.00909, with a scene-bootstrap 95% interval of [0.000744, 0.0177], but its 2048-record and complete-support intervals include zero. A proposal-level replay further confirms the switch-utility decomposition, yet none of 432 screened configurations passes the two-half, two-seed robustness gate. PDT therefore identifies where decision transfer fails or remains indeterminate across proxy, subset, aggregate, and selection evidence.

Related papers

• ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training [66.72708893922605]
  Post-training of large multimodal models should add new capabilities while preserving those from pre-training.<n>SFT gives explicit target supervision that learns a task from near-zero accuracy, but its off-policy targets move the model far enough to cause forgetting.<n>We introduce ReDraft, which obtains both from the model's own failures.
  arXiv  Detail & Related papers  (2026-09-15T04:59:03Z)
• RecGPT-Mobile-V2 Technical Report [22.10290138930905]
  RecGPT-Mobile-V2 is an end-to-end framework that treats intent quality and execution efficiency as coupled objectives within a staged design.<n>The framework transforms heterogeneous interactions into an evidence-preserving trajectory, establishes a recommendation-native foundation through domain adaptation and supervised alignment.<n>Online retrieval analysis indicates that the Query recall channel retrieves inventory complementary to that surfaced by established recall channels.
  arXiv  Detail & Related papers  (2026-08-25T09:23:17Z)
• DREAM Technical Report [53.37525197047151]
  We present DREAM, an autonomous optimization control architecture that adds a perception-aware, orchestrable, and auditable policy layer atop existing pipelines without replacing them.<n> DREAM has two core components. First, a three-tier Intent Engine fuses on-device signals into structured L0/L1/L2 intent representations; its edge-cloud trigger chain reduces reporting volume to approximately 8.7%.<n>Second, a Meta Engine uses a MetaModel for layered M1-to-M2-to-M3 reasoning: intent summarization, strategy planning informed by Strategy Memory, and parameter translation. It dispatches the resulting parameters through a unified outlet with
  arXiv  Detail & Related papers  (2026-08-10T10:35:32Z)
• Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features [4.996631858286914]
  Planning performance is largely insensitive to the tested video-noise levels, whereas strong trajectories can already be decoded from intermediate layers.<n>We introduce Adaptive-WAM, a quality-aware multi-exit planner built on a Wan2.2-5B backbone.
  arXiv  Detail & Related papers  (2026-08-06T13:13:07Z)
• A Self-Triggered Agentic Push Recommendation System [77.13502692161426]
  Push notification is a critical recommendation scenario on large-scale platforms.<n>We propose a proactive, Self-Triggered End-to-end Agentic Push Recommendation System.<n>STEPS is already fully deployed at Douyin with over 1 billion users.
  arXiv  Detail & Related papers  (2026-08-03T09:20:53Z)
• Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade [0.0]
  Under paired exact-reset physical outcomes, can a Medium-derived interface predict when switching to a separately frozen Full predictor improve task-specific decision loss enough to justify sequential overhead?<n>Our contribution is a paired evaluation and audit protocol, not a new generic routing rule.
  arXiv  Detail & Related papers  (2026-07-30T18:35:13Z)
• CLEAR: Cognition and Latent Evaluation for Adaptive Routing in End-to-End Autonomous Driving [19.474428775260034]
  We propose CLEAR, a framework that combines ultra-fast generative planning with deep semantic reasoning.<n> CLEAR employs Drive-JEPA as the visual encoder and replaces the multi-step denoising chain with a single-step conditional drift in a VAE latent space.<n>On the NAVSIM v1 benchmark, CLEAR achieves a state-of-the-art PDMS of 93.7.
  arXiv  Detail & Related papers  (2026-06-04T14:32:10Z)
• A Blueprint for Self-Evolving Coding Agents in Vehicle Aerodynamic Drag Prediction [9.020568132598827]
  We present a contract-centric blueprint for self-evolving coding agents that discover executable surrogate pipelines for predicting drag coefficient $C_d$ under industrial constraints.<n>The method formulates surrogate discovery as constrained optimization over programs, not static model instances.<n>A hard evaluation contract enforces leakage prevention, deterministic replay, multi-seed, robustness and resource budgets before any candidate is admitted.
  arXiv  Detail & Related papers  (2026-03-23T08:36:57Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Foundation Models for Logistics: Toward Certifiable, Conversational Planning Interfaces [59.80143393787701]
  Large language models (LLMs) can handle uncertainty and promise to accelerate replanning while lowering the barrier to entry.<n>We introduce a neurosymbolic framework that pairs the accessibility of natural-language dialogue with verifiable guarantees on goal interpretation.<n>A lightweight model, fine-tuned on just 100 uncertainty-filtered examples, surpasses the zero-shot performance of GPT-4.1 while cutting inference latency by nearly 50%.
  arXiv  Detail & Related papers  (2025-07-15T14:24:01Z)
• Reinforcement Learning with a Terminator [80.34572413850186]
  We learn the parameters of the TerMDP and leverage the structure of the estimation problem to provide state-wise confidence bounds. We use these to construct a provably-efficient algorithm, which accounts for termination, and bound its regret.
  arXiv  Detail & Related papers  (2022-05-30T18:40:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.