paper-with-me

Papers

Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning

2025-12-30 · Zhenghao "Mark" Peng, Wenhao Ding, Yurong You, Yuxiao Chen, Wenjie Luo, Thomas Tian, Yulong Cao, Apoorva Sharma, Danfei Xu, Boris Ivanovic, Boyi Li, Bolei Zhou, Yan Wang, Marco Pavone arxiv

Recent reasoning-augmented Vision-Language-Action (VLA) models have improved the interpretability of end-to-end autonomous driving by generating intermediate reasoning traces. Yet these models primarily describe what they perceive and intend to do, rarely questioning whether their planned actions are safe or appropriate. This work introduces Counterfactual VLA (CF-VLA), a self-reflective VLA framework that enables the model to reason about and revise its planned actions before execution. CF-VLA first generates time-segmented meta-actions that summarize driving intent, and then performs counterfactual reasoning conditioned on both the meta-actions and the visual context. This step simulates potential outcomes, identifies unsafe behaviors, and outputs corrected meta-actions that guide the final trajectory generation. To efficiently obtain such self-reflective capabilities, we propose a rollout-filter-label pipeline that mines high-value scenes from a base (non-counterfactual) VLA's rollouts and labels counterfactual reasoning traces for subsequent training rounds. Experiments on large-scale driving datasets show that CF-VLA improves trajectory accuracy by up to 17.6%, enhances safety metrics by 20.5%, and exhibits adaptive thinking: it only enables counterfactual reasoning in challenging scenarios. By transforming reasoning traces from one-shot descriptions to causal self-correction signals, CF-VLA takes a step toward self-reflective autonomous driving agents that learn to think before they act.

📄 PDF Abstract BibTeX arXiv:2512.24426

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Driving

Similar Papers 제목 키워드 기반

C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving

2026-05-11 · Kefei Tian, Yuansheng Lian, Kai Yang, Xiangdong Chen 외 arxiv

Safety-critical planning in complex environments, particularly at urban intersections, remains a fundamental challenge for autonomous driving. Existing methods, whether rule-based or data-driven, frequently struggle to c…

Autonomous Driving

CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human

2025-09-18 · Nan Sun, Yongchang Li, Chenxu Wang, Huiying Li 외 arxiv

In this work, we present CollabVLA, a self-reflective vision-language-action framework that transforms a standard visuomotor policy into a collaborative assistant. CollabVLA tackles key limitations of prior VLAs, includi…

Causal Reflection with Language Models

2025-08-06 · Abi Aryan, Zac Liu arxiv

While LLMs exhibit impressive fluency and factual recall, they struggle with robust causal reasoning, often relying on spurious correlations and brittle patterns. Similarly, traditional Reinforcement Learning agents also…

Reinforcement Learning

EvolveNav: Self-Improving Embodied Reasoning for LLM-Based Vision-Language Navigation

2025-06-02 · Bingqian Lin, Yunshuang Nie, Khun Loun Zai, Ziming Wei 외

Building Vision-Language Navigation (VLN) agents which can navigate following natural language instructions is a long-standing goal in human-robot interaction applications. Recent studies have revealed the potential of t…

NavigateVision-Language Navigation

Counterfactual Self-Questioning for Stable Policy Optimization in Language Models

2025-12-31 · Mandar Parab arxiv

Recent work on language model self-improvement shows that models can refine their own reasoning through reflection, verification, debate, or self-generated rewards. However, most existing approaches rely on external crit…

Mathematical Reasoning