# Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling

arXiv: https://arxiv.org/abs/2408.17355 · HTML: https://mlsanity.com/paper/2408.17355/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 72 references that are in the map.
- First posted on arXiv 30 Aug 2024.

## Builds on (most cited first, 30 of 53)

- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation](https://mlsanity.com/paper/2401.02117/) (2024)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies](https://mlsanity.com/paper/2304.10573/) (2023)
- [Behavior Transformers: Cloning k modes with one stone](https://mlsanity.com/paper/2206.11251/) (2022)
- [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://mlsanity.com/paper/2402.02057/) (2024)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [Beam Search Strategies for Neural Machine Translation](https://mlsanity.com/paper/1702.01806/) (2017)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators](https://mlsanity.com/paper/2309.13037/) (2023)
- [RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking](https://mlsanity.com/paper/2309.01918/) (2023)
- [Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation](https://mlsanity.com/paper/2405.07503/) (2024)
- [Behavior Generation with Latent Actions](https://mlsanity.com/paper/2403.03181/) (2024)

## Built on by (most cited first, 30 of 52)

- [Leave No Observation Behind: Real-time Correction for VLA Action Chunks](https://mlsanity.com/paper/2509.23224/) (2025)
- [DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance](https://mlsanity.com/paper/2506.13922/) (2025)
- [Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models](https://mlsanity.com/paper/2505.21200/) (2025)
- [Adaptive Action Chunking at Inference-time for Vision-Language-Action Models](https://mlsanity.com/paper/2604.04161/) (2026)
- [Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment](https://mlsanity.com/paper/2602.12281/) (2026)
- [FASTER: Rethinking Real-Time Flow VLAs](https://mlsanity.com/paper/2603.19199/) (2026)
- [World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry](https://mlsanity.com/paper/2604.01985/) (2026)
- [VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon](https://mlsanity.com/paper/2607.01804/) (2026)
- [FutureRTC: Real-Time Robot Execution with Anticipatory-Conditioned Action Chunking](https://mlsanity.com/paper/2607.24008/) (2026)
- [Long-Horizon Manipulation via Trace-Conditioned VLA Planning](https://mlsanity.com/paper/2604.21924/) (2026)
- [SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policies](https://mlsanity.com/paper/2607.04609/) (2026)
- [VPWEM: Non-Markovian Visuomotor Policy with Working and Episodic Memory](https://mlsanity.com/paper/2603.04910/) (2026)
- [TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation](https://mlsanity.com/paper/2605.25547/) (2026)
- [vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models](https://mlsanity.com/paper/2606.08094/) (2026)
- [Dreaming the Unseen: World Model-regularized Diffusion Policy for Out-of-Distribution Robustness](https://mlsanity.com/paper/2603.21017/) (2026)
- [Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL](https://mlsanity.com/paper/2608.30640/) (2026)
- [Knowing When to Stop: Adaptive Action Chunking via Internal Cross-Attention Dynamics in VLAs](https://mlsanity.com/paper/2609.00908/) (2026)
- [MINERVA: How Small Can a Manipulation Policy Be and Still Solve LIBERO?](https://mlsanity.com/paper/2609.03715/) (2026)
- [Post-Training and Test-Time Scaling of Generative Agent Behavior Models for Interactive Autonomous Driving](https://mlsanity.com/paper/2512.13262/) (2025)
- [Tube Diffusion Policy: Reactive Visual-Tactile Policy Learning for Contact-rich Manipulation](https://mlsanity.com/paper/2604.23609/) (2026)
- [Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving](https://mlsanity.com/paper/2606.11019/) (2026)
- [ChainVLA: Chaining Vision-Language-Action Queries through a Unified Execution State for Long-Horizon Manipulation](https://mlsanity.com/paper/2608.02326/) (2026)
- [Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency](https://mlsanity.com/paper/2608.23831/) (2026)
- [ACG: Action Coherence Guidance for Flow-based Vision-Language-Action models](https://mlsanity.com/paper/2510.22201/) (2025)
- [Habilis-β: A Fast-Motion and Long-Lasting On-Device Vision-Language-Action Model](https://mlsanity.com/paper/2602.18813/) (2026)
- [Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models](https://mlsanity.com/paper/2605.11459/) (2026)
- [DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigation](https://mlsanity.com/paper/2608.12308/) (2026)
- [World-Coherent Decoding: Self-Verifying Test-Time Planning for World Action Models](https://mlsanity.com/paper/2609.02159/) (2026)
- [GROOVE: Geometry-Guided Reduction of Operational-Space Jerk in VLA Execution](https://mlsanity.com/paper/2609.13695/) (2026)
- [CroSTAta: Cross-State Transition Attention Transformer for Robotic Manipulation](https://mlsanity.com/paper/2510.00726/) (2025)

## Abstract (arXiv)

Predicting and executing a sequence of actions without intermediate replanning, known as action chunking, is increasingly used in robot learning from human demonstrations. Yet, its effects on the learned policy remain inconsistent: some studies find it crucial for achieving strong results, while others observe decreased performance. In this paper, we first dissect how action chunking impacts the divergence between a learner and a demonstrator. We find that action chunking allows the learner to better capture the temporal dependencies in demonstrations but at the cost of reduced reactivity to unexpected states. To address this tradeoff, we propose Bidirectional Decoding (BID), a test-time inference algorithm that bridges action chunking with closed-loop adaptation. At each timestep, BID samples multiple candidate predictions and searches for the optimal one based on two criteria: (i) backward coherence, which favors samples that align with previous decisions; (ii) forward contrast, which seeks samples of high likelihood for future plans. By coupling decisions within and across action chunks, BID promotes both long-term consistency and short-term reactivity. Experimental results show that our method boosts the performance of two state-of-the-art generative policies across seven simulation benchmarks and two real-world tasks. Code and videos are available at https://bid-robot.github.io.