pith. sign in

arxiv: 2606.07723 · v1 · pith:PPA2S7JNnew · submitted 2026-06-05 · 💻 cs.RO

VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation

Siyi Chen , Hugo Hadfield , Alex Zook , Mikaela Angelina Uy , Chan Hee Song , Erwin Coumans , Xuning Yang , Faisal Ladhak
show 4 more authors
Qing Qu Stan Birchfield Jonathan Tremblay Valts Blukis
This is my paper

Pith reviewed 2026-06-27 21:38 UTC · model grok-4.3

classification 💻 cs.RO
keywords open-vocabulary manipulationlong-horizon tasksvision-language modelrobot orchestrationinterruptible toolsphysical agentRoboVoLo benchmarkVLA
0
0 comments X

The pith

A VLM orchestrates robot capabilities as interruptible tools to manage open-vocabulary long-horizon manipulation.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that a vision-language model can run a closed agent loop to plan, execute, monitor, and recover in physical robot tasks with flexible instructions and complex scenes. It does so by treating a VLA, vision models, and action primitives as tools that the VLM can interrupt and steer mid-rollout. This matters because physical environments do not pause for reasoning, unlike virtual agents. The claim is tested on the RoboVoLo benchmark, which measures success and failure modes across common sense, memory, references, and knowledge, plus real-robot trials where the method beats single VLA or VLM baselines.

Core claim

VoLoAgent uses a VLM to plan, monitor, and recover by treating a VLA/WAM as an interruptible tool it steers mid-rollout alongside vision models and action primitives. This addresses open-vocabulary long-horizon manipulation in a physical world where the timing of decisions, actions, and tool calls matters because the environment does not pause for reasoning.

What carries the argument

Physical Orchestration: the closed agent loop in which a VLM orchestrates heterogeneous robot capabilities as interruptible tools, enabling adaptive planning and recovery when timing is critical.

If this is right

  • VoLoAgent substantially outperforms single VLA/VLM or tool-based systems on long-horizon open-vocabulary tasks.
  • The RoboVoLo benchmark supplies both task-level success rates and failure-mode diagnostics across common sense, memory/state tracking, complex references, and world knowledge.
  • Real-robot experiments confirm the method works outside simulation for physical manipulation.
  • The interruptible-tool design supports recovery from failures during multi-object, flexible-instruction sequences.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same orchestration pattern could be tested on tasks that combine manipulation with navigation where timing between subtasks is equally strict.
  • Adding more vision primitives as tools might reduce specific failure modes the benchmark already flags.
  • The approach leaves open whether the VLM needs explicit training on timing constraints or can learn them from the tool interface alone.

Load-bearing premise

A VLM can reliably plan, monitor, and recover by treating a VLA as an interruptible tool it steers mid-rollout alongside other models in a physical setting where timing of actions matters.

What would settle it

A set of RoboVoLo tasks or real-robot trials in which VoLoAgent shows no improvement over single VLA or VLM baselines on metrics for memory tracking or complex reference resolution.

Figures

Figures reproduced from arXiv: 2606.07723 by Alex Zook, Chan Hee Song, Erwin Coumans, Faisal Ladhak, Hugo Hadfield, Jonathan Tremblay, Mikaela Angelina Uy, Qing Qu, Siyi Chen, Stan Birchfield, Valts Blukis, Xuning Yang.

Figure 1
Figure 1. Figure 1: VoLo overview. VoLoAgent plans, monitors (e.g., subgoal complete), and uses tools (e.g., VLA, SAM3) to act and recover from failures (e.g., wrong object). RoboVoLo is a high-fidelity benchmark for evaluating and diagnosing open-vocabulary long-horizon manipulation. Abstract Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while a… view at source ↗
Figure 2
Figure 2. Figure 2: RoboVoLo benchmark. 126 long-horizon manipulation tasks across 15 categories, grouped into four capability suites: Common Sense (infer intent from scene context), Memory (track state across actions), Complex References (resolve spatial, ordinal, size, and negation cues), and World Knowledge (apply external knowledge spanning math, art, chemistry, and recycling). Each panel shows one representative task wit… view at source ↗
Figure 3
Figure 3. Figure 3: VoLoAgent system. A VLM agent plans, monitors, and orchestrates tools (VLA/WAM rollouts, perception models, grasp/place primitives) through one closed-loop control law. The agent can interrupt a VLA rollout and switch to a different tool when execution drifts. these capabilities or a fixed pipeline. With physical orchestration we emphasize the need to handle all three together, for an open-vocabulary agent… view at source ↗
Figure 4
Figure 4. Figure 4: Process comparison on two open-vocabulary long-horizon tasks, one row per system. Red tags mark failure events and green tags mark grasp-tool recovery events. The behaviors shown are described in Sec. 5.2 [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: World failure analysis tracing episodes through failures, recovery, and outcomes for 𝜋0.5 (left) and VoLoAgent (right). Major failure subtypes: stuck, WOP=wrong object picked, WTP=wrong target place. Band thickness is proportional to the number of episodes. World Failures [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: VLM failure audit. Left: one example per failure type (Planning, Completion-monitor, Failure-monitor, Tool-use). Right: per-VLM error counts across 𝑛=90 episodes; segment colors match the example tag colors. Qwen3-VL-8B reaches 23% of the ceiling error counts, Claude Opus 4.6 only 5%. Error definitions in Appendix K. VLM Failures [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Real robot examples. VoLoAgent monitors and recovers from failures such as wrong place destination, wrong object pick in the real world as well [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Common Sense suite – task examples. 8 representative initial-scene views from the Common Sense suite of RoboVoLo; each panel shows the task category (italics) and its instruction. alongside RGB; the grasp primitive consumes the front-camera depth, and the place primitive consumes the front-camera depth together with a Molmo2 2-D point. The VLA does not see depth. Scene assets. RoboVoLo expands RoboLab’s as… view at source ↗
Figure 9
Figure 9. Figure 9: Memory suite – task examples. 6 representative initial-scene views from the Memory suite of RoboVoLo; each panel shows the task category (italics) and its instruction. F.1. Paired Sign-Flip Randomization Test (Main-Results and Component-Ablation tables in the main paper) Setup. Fix two methods 𝐴 and 𝐵 and the set of tasks 𝒯 on which both methods were run with 𝐾=3 matched￾seed trials per task. For task 𝑖 ∈ … view at source ↗
Figure 10
Figure 10. Figure 10: Complex References suite – task examples. 8 representative initial-scene views from the Complex References suite of RoboVoLo; each panel shows the task category (italics) and its instruction. (a) Art. “Complete the stick figure by placing the missing head.” (b) Art. “Complete the stick figure by placing the missing head.” (c) Chem. “Complete the wa￾ter molecule by adding the missing element to the bowl.” … view at source ↗
Figure 11
Figure 11. Figure 11: World Knowledge suite – task examples. 8 representative initial-scene views from the World Knowledge suite of RoboVoLo; each panel shows the task category (italics) and its instruction. Tasks with 𝑑𝑖=0 contribute zero in every flip and are kept, matching standard sign-flip convention. The two-sided p-value for the observed ¯𝑑obs is the tail mass 𝑝 = Pr 𝜀∼Unif{±1}𝑁 [︁ ⃒ ⃒ ¯𝑑 ⋆ (𝜀) ⃒ ⃒ ≥ | ¯𝑑obs| ]︁ . (4) 2… view at source ↗
Figure 12
Figure 12. Figure 12: The 501 new RoboVoLo assets. Every object added on top of RoboLab’s existing library is shown: 247 Lightwheel SimReady household items plus 254 task-specific assets (118 periodic-table element cubes, 120 geometric art primitives, 16 math digit/operator cubes). Each tile is the Isaac Sim render of a single asset, randomly ordered. Computation. For 𝑁 ≤ 24 we evaluate Eq. 4 exactly by enumerating all 2 𝑁 sig… view at source ↗
Figure 13
Figure 13. Figure 13: reports the outcome-flow Sankey diagrams for the two intermediate ablations omitted from the main-paper Sankey figure in the main text: VoLoAgent (No VLA), which replaces the policy with VLM-driven primitives, and VoLoAgent (Only VLA), which keeps the VLA + VLM monitor but disables tool-augmented recovery. Tool-Chain Episodes (90) No failures (18) Failures (72) All recovered (20) Unrec: stuck (42) Unrec: … view at source ↗
read the original abstract

Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while adaptively planning, executing, monitoring, and recovering from failures. We address these demands with a closed agent loop in which a VLM orchestrates heterogeneous robot capabilities as interruptible tools. Unlike in virtual AI agents, the timing of decisions, actions and tool calls is important in a physical world that does not pause for reasoning. We refer to this setting as Physical Orchestration, and propose VoLoAgent, a VLM that plans, monitors, and recovers by treating a VLA/WAM as an interruptible tool it steers mid-rollout alongside vision models and action primitives. To evaluate these long-horizon capabilities, we introduce RoboVoLo, a high-fidelity benchmark for open-vocabulary long-horizon manipulation across common sense, memory/state tracking, complex references, and world knowledge, with both task-level success and failure-mode diagnostics. Experiments show VoLoAgent substantially outperforms single VLA/VLM or tool-based systems, with validation on real-robot experiments. Project page: https://chicychen.github.io/VoLo/

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. The manuscript introduces VoLoAgent, a closed-loop VLM agent for open-vocabulary long-horizon manipulation. It treats a VLA/WAM as an interruptible tool that the VLM steers mid-rollout, together with vision models and action primitives, under the framing of 'Physical Orchestration' where timing of decisions and tool calls matters because the physical world does not pause. The paper also presents the RoboVoLo benchmark covering common-sense reasoning, memory/state tracking, complex references, and world knowledge, with both task success metrics and failure-mode diagnostics. Experiments are reported to show substantial outperformance versus single VLA/VLM or tool-based baselines, with real-robot validation.

Significance. If the empirical claims are supported by the full methods and diagnostics, the work would contribute a concrete integration strategy for high-level VLM reasoning with low-level robot execution in long-horizon settings. The benchmark's inclusion of failure-mode analysis is a constructive addition for the robotics community. The explicit attention to physical timing distinguishes the setting from virtual agents and is a relevant direction.

major comments (1)
  1. [Abstract / Approach] Abstract and approach description: the manuscript states that 'the timing of decisions, actions and tool calls is important in a physical world that does not pause for reasoning' and that the VLM steers the VLA 'mid-rollout', yet no concrete synchronization mechanism (decision frequency, latency bounds, state buffering, or safety interlocks) is supplied. This assumption is load-bearing for both the Physical Orchestration claim and the real-robot outperformance results.
minor comments (1)
  1. [Abstract] The project page is referenced but no information is given on benchmark release, code, or exact task definitions needed for independent verification.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive feedback and positive evaluation of the work's potential. We respond to the single major comment below.

read point-by-point responses

  1. Referee: [Abstract / Approach] Abstract and approach description: the manuscript states that 'the timing of decisions, actions and tool calls is important in a physical world that does not pause for reasoning' and that the VLM steers the VLA 'mid-rollout', yet no concrete synchronization mechanism (decision frequency, latency bounds, state buffering, or safety interlocks) is supplied. This assumption is load-bearing for both the Physical Orchestration claim and the real-robot outperformance results.

    Authors: We agree that explicit details on synchronization are necessary to fully support the Physical Orchestration framing and the real-robot claims. The manuscript presents the high-level concept and empirical outcomes but does not specify decision frequency, latency bounds, state buffering, or safety interlocks. In revision we will add a new subsection (likely under Implementation or Experimental Setup) that documents the closed-loop timing parameters used, including VLM invocation rate, buffering of visual state during VLA rollouts, observed latencies on the real platform, and any interlocks applied to prevent unsafe interruptions. These additions will directly address the load-bearing nature of the timing assumption. revision: yes

Circularity Check

0 steps flagged

Empirical system comparison with no derivations or self-referential reductions

full rationale

The manuscript describes an empirical agent architecture (VoLoAgent) for physical orchestration of VLMs, VLAs, and primitives, evaluated via the RoboVoLo benchmark and real-robot trials. No equations, first-principles derivations, fitted parameters renamed as predictions, or load-bearing self-citations appear in the provided text. All claims reduce to experimental outperformance against baselines rather than any closed mathematical chain, satisfying the default expectation of non-circularity for empirical systems.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review provides no explicit free parameters, axioms, or invented entities; the approach relies on standard VLM and robotics assumptions not detailed here.

pith-pipeline@v0.9.1-grok · 5771 in / 1071 out tokens · 23771 ms · 2026-06-27T21:38:28.765135+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

87 extracted references · 1 canonical work pages · 1 internal anchor

  1. [1]

    ClaudeOpus4.7systemcard

    Anthropic. ClaudeOpus4.7systemcard. https://www.anthropic.com/system-cards, 2026. Anthropic technical report. Also covers Claude Opus 4.6 and Claude Sonnet 4.6. 7

    2026

  2. [2]

    RT-2: Vision-language-action models transfer web knowledge to robotic control

    Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Xi Chen, Krzysztof Choromanski, Tianli Ding, Danny Driess, Avinava Dubey, Chelsea Finn, Pete Florence, Chuyuan Fu, Montse Gonzalez Arenas, Keerthana Gopalakrishnan, Kehang Han, Karol Hausman, Alexander Herzog, Jasmine Hsu, Brian Ichter, Alex Irpan, Nikhil Joshi, Ryan Julian, Dmitry Kalashnikov...

    2023

  3. [3]

    Brown, T

    Lawrence D. Brown, T. Tony Cai, and Anirban DasGupta. Interval estimation for a binomial proportion. Statistical Science, 16(2):101–133, 2001. 30

    2001

  4. [4]

    Enabling failure recovery for on-the-move mobile manipulation

    Ben Burgess-Limerick, Chris Lehnert, Jürgen Leitner, and Peter Corke. Enabling failure recovery for on-the-move mobile manipulation. InIEEE ICRA Workshop on Robotic Perception and Mapping: Frontier Vision and Learning Techniques, 2023. ICRA 2023 Workshop on Robot Failures; arXiv:2305.08351. 4

    arXiv 2023

  5. [5]

    SAM 3: Segment anything with concepts

    Nicolas Carion, Laura Gustafson, Yuan-Ting Hu, Shoubhik Debnath, Ronghang Hu, Didac Suris, Chaitanya Ryali, Kalyan Vasudev Alwala, Haitham Khedr, Andrew Huang, Jie Lei, Tengyu Ma, Baishan Guo, Arpit Kalla, Markus Marks, Joseph Greer, Meng Wang, Peize Sun, Roman Rädle, Triantafyllos Afouras, Effrosyni Mavroudi, Katherine Xu, Tsung-Han Wu, Yu Zhou, Liliane ...

    Pith/arXiv arXiv 2025

  6. [6]

    GR-2: A generative video-language-action model with web-scale knowledge for robot manipulation.arXiv preprint arXiv:2410.06158, 2024

    Chi-Lam Cheang, Guangzeng Chen, Ya Jing, Tao Kong, Hang Li, Yifeng Li, Yuxiao Liu, Hongtao Wu, Jiafeng Xu, Yichu Yang, Hanbo Zhang, and Minzhao Zhu. GR-2: A generative video-language-action model with web-scale knowledge for robot manipulation.arXiv preprint arXiv:2410.06158, 2024. 2, 3

    Pith/arXiv arXiv 2024

  7. [7]

    Lingling Chen, Zongyao Lyu, and William J. Beksi. Reconvla: An uncertainty-guided and failure-aware vision-language-action framework for robotic control.arXiv preprint arXiv:2604.16677, 2026. 3

    Pith/arXiv arXiv 2026

  8. [8]

    SpaceTools: Tool-augmented spatial reasoning via double interactive rl.CVPR, 2026

    Siyi Chen, Mikaela Angelina Uy, Chan Hee Song, Faisal Ladhak, Adithyavairavan Murali, Qing Qu, Stan Birchfield, Valts Blukis, and Jonathan Tremblay. SpaceTools: Tool-augmented spatial reasoning via double interactive rl.CVPR, 2026. 2, 19

    2026

  9. [9]

    RMBench: Memory-dependent robotic manipulation benchmark with insights into policy design.arXiv preprint arXiv:2603.01229, 2026

    Tianxing Chen, Yuran Wang, Mingleyang Li, Yan Qin, Hao Shi, Zixuan Li, Yifan Hu, Yingsheng Zhang, Kaixuan Wang, Yue Chen, Hongcheng Wang, Renjing Xu, Ruihai Wu, Yao Mu, Yaodong Yang, Hao Dong, and Ping Luo. RMBench: Memory-dependent robotic manipulation benchmark with insights into policy design.arXiv preprint arXiv:2603.01229, 2026. 3 10 VoLo: A Physical...

    arXiv 2026

  10. [10]

    Molmo2: Open weights and data for vision-language models with video understanding and grounding.arXiv preprint arXiv:2601.10611, 2026

    Christopher Clark, Jieyu Zhang, Zixian Ma, Jae Sung Park, Mohammadreza Salehi, Rohun Tripathi, Sangho Lee, Zhongzheng Ren, Chris Dongjoo Kim, Yinuo Yang, Vincent Shao, Yue Yang, Weikai Huang, Ziqi Gao, Taira Anderson, Jianrui Zhang, Jitesh Jain, George Stoica, Winson Han, Ali Farhadi, and Ranjay Krishna. Molmo2: Open weights and data for vision-language m...

    Pith/arXiv arXiv 2026

  11. [11]

    RACER: Rich language-guided failure recovery policies for imitation learning.arXiv preprint arXiv:2409.14674, 2024

    Yinpei Dai, Jayjun Lee, Nima Fazeli, and Joyce Chai. RACER: Rich language-guided failure recovery policies for imitation learning.arXiv preprint arXiv:2409.14674, 2024. 3

    arXiv 2024

  12. [12]

    Smith, Hannaneh Hajishirzi, Ross Girshick, Ali Farhadi, and Aniruddha Kembhavi

    Matt Deitke, Christopher Clark, Sangho Lee, Rohun Tripathi, Yue Yang, Jae Sung Park, Mohammadreza Salehi, Niklas Muennighoff, Kyle Lo, Luca Soldaini, Jiasen Lu, Taira Anderson, Erin Bransom, Kiana Ehsani, Huong Ngo, YenSung Chen, Ajay Patel, Mark Yatskar, Chris Callison-Burch, Andrew Head, Rose Hendrix, Favyen Bastani, Eli VanderBilt, Nathan Lambert, Yvon...

    Pith/arXiv arXiv 2024

  13. [13]

    MolmoBot: Large-scale simulation enables zero-shot manipulation.arXiv preprint arXiv:2603.16861, 2026

    Abhay Deshpande, Maya Guru, Rose Hendrix, Snehal Jauhri, Ainaz Eftekhar, Rohun Tripathi, Max Argus, Jordi Salvador, Haoquan Fang, Matthew Wallingford, Wilbert Pumacay, Yejin Kim, Quinn Pfeifer, Ying- Chun Lee, Piper Wolters, Omar Rayyan, Mingtong Zhang, Jiafei Duan, Karen Farley, Winson Han, Eli VanderBilt, Dieter Fox, Ali Farhadi, Georgia Chalvatzaki, Dh...

    arXiv 2026

  14. [14]

    Manipulate-anything: Automating real-world robots using vision-language models

    Jiafei Duan, Wentao Yuan, Wilbert Pumacay, Yi Ru Wang, Kiana Ehsani, Dieter Fox, and Ranjay Krishna. Manipulate-anything: Automating real-world robots using vision-language models. InCoRL, 2024. 3

    2024

  15. [15]

    AHA: A vision-language-model for detecting and reasoning over failures in robotic manipulation

    Jiafei Duan, Wilbert Pumacay, Nishanth Kumar, Yi Ru Wang, Shulin Tian, Wentao Yuan, Ranjay Krishna, Dieter Fox, Ajay Mandlekar, and Yijie Guo. AHA: A vision-language-model for detecting and reasoning over failures in robotic manipulation. InICLR, 2025. 3

    2025

  16. [16]

    Edgington and Patrick Onghena.Randomization Tests

    Eugene S. Edgington and Patrick Onghena.Randomization Tests. Chapman and Hall/CRC, Boca Raton, FL, 4 edition, 2007. 7, 27

    2007

  17. [17]

    MolmoAct2: Action reasoning models for real-world deployment.arXiv preprint arXiv:2605.02881, 2026

    Haoquan Fang, Jiafei Duan, Donovan Clay, Sam Wang, Shuo Liu, Weikai Huang, Xiang Fan, Wei-Chuan Tsai, Shirui Chen, Yi Ru Wang, Shanli Xing, Jaemin Cho, Jae Sung Park, Ainaz Eftekhar, Peter Sushko, Karen Farley, Angad Wadhwa, Cole Harrison, Winson Han, Ying-Chun Lee, Eli VanderBilt, Rose Hendrix, Suveen Ellawela, Lucas Ngoo, Joyce Chai, Zhongzheng Ren, Ali...

    Pith/arXiv arXiv 2026

  18. [18]

    Reflective planning: Vision-language models for multi-stage long-horizon robotic manipulation

    Yunhai Feng, Jiaming Han, Zhuoran Yang, Xiangyu Yue, Sergey Levine, and Jianlan Luo. Reflective planning: Vision-language models for multi-stage long-horizon robotic manipulation. InConference on Robot Learning (CoRL), 2025. arXiv:2502.16707. 3

    arXiv 2025

  19. [19]

    Barry, Kris Kitani, and George Konidaris

    Jiahui Fu, Junyu Nan, Lingfeng Sun, Hongyu Li, Jianing Qian, Jennifer L. Barry, Kris Kitani, and George Konidaris. NovaPlan: Zero-shot long-horizon manipulation via closed-loop video language planning. arXiv preprint arXiv:2602.20119, 2026. 3

    arXiv 2026

  20. [20]

    CaP-X: A framework for benchmarking and improving coding agents for robot manipulation.arXiv preprint arXiv:2603.22435, 2026

    Max Fu, Justin Yu, Karim El-Refai, Ethan Kou, Haoru Xue, Huang Huang, Wenli Xiao, Guanzhi Wang, Fei-Fei Li, Guanya Shi, et al. CaP-X: A framework for benchmarking and improving coding agents for robot manipulation.arXiv preprint arXiv:2603.22435, 2026. 2, 3, 7 11 VoLo: A Physical Orchestrator for Open-VocabularyLong-Horizon Manipulation

    arXiv 2026

  21. [21]

    Shenyuan Gao, William Liang, Kaiyuan Zheng, Ayaan Malik, Seonghyeon Ye, Sihyun Yu, Wei-Cheng Tseng, Yuzhu Dong, Kaichun Mo, Chen-Hsuan Lin, Qianli Ma, Seungjun Nah, Loic Magne, Jiannan Xiang, Yuqi Xie, Ruijie Zheng, Dantong Niu, You Liang Tan, K. R. Zentner, George Kurian, Suneel Indupuru, Pooya Jannaty, Jinwei Gu, Jun Zhang, Jitendra Malik, Pieter Abbeel...

    Pith/arXiv arXiv 2026

  22. [22]

    SAFE: Multitask failure detection for vision-language-action models.arXiv preprint arXiv:2506.09937, 2025

    Qiao Gu, Yuanliang Ju, Shengxiang Sun, Igor Gilitschenski, Haruki Nishimura, Masha Itkina, and Florian Shkurti. SAFE: Multitask failure detection for vision-language-action models.arXiv preprint arXiv:2506.09937, 2025. 3

    arXiv 2025

  23. [23]

    RoboCerebra: A large-scale benchmark for long-horizon robotic manipulation evaluation

    Songhao Han, Boxiang Qiu, Yue Liao, Siyuan Huang, Chen Gao, Shuicheng Yan, and Si Liu. RoboCerebra: A large-scale benchmark for long-horizon robotic manipulation evaluation. InNeurIPS, 2025. 3, 31, 32

    2025

  24. [24]

    LIBERO+: Robust language-image foundation models for robotic manipulation

    Senthooran Huang and LIBERO-Plus contributors. LIBERO+: Robust language-image foundation models for robotic manipulation. arXiv preprint, 2025. Language-rephrasing eval suite for LIBERO. 31

    2025

  25. [25]

    Inner monologue: Embodied reasoning through planning with language models

    Wenlong Huang, Fei Xia, Ted Xiao, Harris Chan, Jacky Liang, Pete Florence, Andy Zeng, Jonathan Tompson, Igor Mordatch, Yevgen Chebotar, Pierre Sermanet, Noah Brown, Tomas Jackson, Linda Luu, Sergey Levine, Karol Hausman, and Brian Ichter. Inner monologue: Embodied reasoning through planning with language models. InCoRL, 2022. 3

    2022

  26. [26]

    arXiv preprint arXiv:2511.14759, 2025

    Physical Intelligence, Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Kevin Black, Ken Conley, Grace Connors, James Darpinian, Karan Dhabalia, Jared DiCarlo, et al.𝜋* 0.6: a VLA that learns from experience. arXiv preprint arXiv:2511.14759, 2025. 2, 3

    Pith/arXiv arXiv 2025

  27. [27]

    2, 3, 5, 7, 25

    Physical Intelligence, Kevin Black, Noah Brown, James Darpinian, Karan Dhabalia, Danny Driess, Adnan Esmail, Michael Equi, Chelsea Finn, Niccolo Fusai, et al.𝜋0.5: a vision-language-action model with open-world generalization.arXiv preprint, 2025. 2, 3, 5, 7, 25

    2025

  28. [28]

    Physical Intelligence, Bo Ai, Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Greg Balke, Kevin Black, George Bokinsky, Shihao Cao, Thomas Charbonnier, et al.𝜋0.7: a steerable generalist robotic foundation model with emergent capabilities.arXiv preprint arXiv:2604.15483, 2026. 2, 3

    Pith/arXiv arXiv 2026

  29. [29]

    Stephen James, Zicong Ma, David Rovick Arrojo, and Andrew J. Davison. RLBench: The robot learning benchmark & learning environment.IEEE Robotics and Automation Letters, 5(2):3019–3026, 2020. 3

    2020

  30. [30]

    VIMA: General robot manipulation with multimodal prompts

    Yunfan Jiang, Agrim Gupta, Zichen Zhang, Guanzhi Wang, Yongqiang Dou, Yanjun Chen, Li Fei-Fei, Anima Anandkumar, Yuke Zhu, and Linxi Fan. VIMA: General robot manipulation with multimodal prompts. InICML, 2023. 3

    2023

  31. [31]

    DROID: A large-scale in-the-wild robot manipulation dataset

    Alexander Khazatsky, Karl Pertsch, Suraj Nair, Ashwin Balakrishna, Sudeep Dasari, Siddharth Karamcheti, Soroush Nasiriany, Mohan Kumar Srirama, et al. DROID: A large-scale in-the-wild robot manipulation dataset. InRobotics: Science and Systems (RSS), 2024. 6, 24, 31, 32

    2024

  32. [32]

    OpenVLA: An open-source vision-language-action model.arXiv preprint arXiv:2406.09246, 2024

    Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti, Ted Xiao, Ashwin Balakrishna, Suraj Nair, Rafael Rafailov, Ethan Foster, Grace Lam, Pannag Sanketi, Quan Vuong, Thomas Kollar, Benjamin Burchfiel, Russ Tedrake, Dorsa Sadigh, Sergey Levine, Percy Liang, and Chelsea Finn. OpenVLA: An open-source vision-language-action model.arXiv preprint arXiv:2406.09246, 2024. 3

    Pith/arXiv arXiv 2024

  33. [33]

    Cosmos Policy: Fine-tuning video models for visuomotor control and planning.arXiv preprint arXiv:2601.16163, 2026

    Moo Jin Kim, Yihuai Gao, Tsung-Yi Lin, Yen-Chen Lin, Yunhao Ge, Grace Lam, Percy Liang, Shuran Song, Ming-Yu Liu, Chelsea Finn, and Jinwei Gu. Cosmos Policy: Fine-tuning video models for visuomotor control and planning.arXiv preprint arXiv:2601.16163, 2026. 2, 3 12 VoLo: A Physical Orchestrator for Open-VocabularyLong-Horizon Manipulation

    Pith/arXiv arXiv 2026

  34. [34]

    MolmoSpaces: A large-scale open ecosystem for robot navigation and manipulation, 2026

    Yejin Kim, Wilbert Pumacay, Omar Rayyan, Max Argus, Winson Han, Eli VanderBilt, Jordi Salvador, Abhay Deshpande, Rose Hendrix, Snehal Jauhri, Shuo Liu, Nur Muhammad Mahi Shafiullah, Maya Guru, Arjun Guru, Ainaz Eftekhar, Karen Farley, Donovan Clay, Jiafei Duan, Piper Wolters, Alvaro Herrasti, Ying-Chun Lee, Georgia Chalvatzaki, Yuchen Cui, Ali Farhadi, Di...

    arXiv 2026

  35. [35]

    MolmoAct: Action reasoning models that can reason in space.arXiv preprint arXiv:2508.07917, 2025

    Jason Lee, Jiafei Duan, Haoquan Fang, Yuquan Deng, Shuo Liu, Boyang Li, Bohan Fang, Jieyu Zhang, Yi Ru Wang, Sangho Lee, Winson Han, Wilbert Pumacay, Angelica Wu, Rose Hendrix, Karen Farley, Eli VanderBilt, Ali Farhadi, Dieter Fox, and Ranjay Krishna. MolmoAct: Action reasoning models that can reason in space.arXiv preprint arXiv:2508.07917, 2025. 3

    Pith/arXiv arXiv 2025

  36. [36]

    Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models

    Zixing Lei, Changxing Liu, Yichen Xiong, Minhao Xiong, Yuanzhuo Ding, Zhipeng Zhang, Weixin Li, and Siheng Chen. Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models. arXiv preprint arXiv:2605.13119, 2026. 3

    Pith/arXiv arXiv 2026

  37. [37]

    BEHAVIOR-1K: A benchmark for embodied AI with 1,000 everyday activities and realistic simulation

    Chengshu Li, Ruohan Zhang, Josiah Wong, Cem Gokmen, Sanjana Srivastava, Roberto Martín-Martín, Chen Wang, Gabrael Levine, Michael Lingelbach, Jiankai Sun, et al. BEHAVIOR-1K: A benchmark for embodied AI with 1,000 everyday activities and realistic simulation. InConference on Robot Learning (CoRL), 2022. 3

    2022

  38. [38]

    Towards efficient and robust manipulation via multi-frame vision-language-action modeling

    Hao Li, Shuai Yang, Yilun Chen, Xinyi Chen, Xiaoda Yang, Yang Tian, Hanqing Wang, Tai Wang, Feng Zhao, Dahua Lin, and Jiangmiao Pang. Towards efficient and robust manipulation via multi-frame vision-language-action modeling. InProceedings of the AAAI Conference on Artificial Intelligence, 2026. Oral. arXiv:2506.19816. 3

    arXiv 2026

  39. [39]

    Causal world modeling for robot control.arXiv preprint arXiv:2601.21998, 2026

    Lin Li, Qihang Zhang, Yiming Luo, Shuai Yang, Ruilin Wang, Fei Han, Mingrui Yu, Zelin Gao, Nan Xue, Xing Zhu, Yujun Shen, and Yinghao Xu. Causal world modeling for robot control.arXiv preprint arXiv:2601.21998, 2026. 2, 3

    Pith/arXiv arXiv 2026

  40. [40]

    Evaluating real-world robot manipulation policies in simulation

    Xuanlin Li, Kyle Hsu, Jiayuan Gu, Karl Pertsch, Oier Mees, Homer Rich Walke, Chuyuan Fu, Ishikaa Lunawat, Isabel Sieh, Sean Kirmani, Sergey Levine, Jiajun Wu, Chelsea Finn, Hao Su, Quan Vuong, and Ted Xiao. Evaluating real-world robot manipulation policies in simulation. InCoRL, 2024. 3

    2024

  41. [41]

    HAMSTER: Hierarchical action models for open-world robot manipulation, 2025

    Yi Li, Yuquan Deng, Jesse Zhang, Joel Jang, Marius Memmel, Raymond Yu, Caelan Reed Garrett, Fabio Ramos, Dieter Fox, Anqi Li, Abhishek Gupta, and Ankit Goyal. HAMSTER: Hierarchical action models for open-world robot manipulation, 2025. 2, 3

    2025

  42. [42]

    Code as policies: Language model programs for embodied control

    Jacky Liang, Wenlong Huang, Fei Xia, Peng Xu, Karol Hausman, Brian Ichter, Pete Florence, and Andy Zeng. Code as policies: Language model programs for embodied control. InICRA, 2023. 2, 3

    2023

  43. [43]

    FailSafe: Reasoning and recovery from failures in vision-language-action models.arXiv preprint arXiv:2510.01642,

    Zijun Lin, Jiafei Duan, Haoquan Fang, Dieter Fox, Ranjay Krishna, Cheston Tan, and Bihan Wen. FailSafe: Reasoning and recovery from failures in vision-language-action models.arXiv preprint arXiv:2510.01642,

    arXiv

  44. [44]

    LIBERO: Bench- marking knowledge transfer for lifelong robot learning

    Bo Liu, Yifeng Zhu, Chongkai Gao, Yihao Feng, Qiang Liu, Yuke Zhu, and Peter Stone. LIBERO: Bench- marking knowledge transfer for lifelong robot learning. InAdvances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, 2023. 2, 3, 31

    2023

  45. [45]

    Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection

    Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, and Lei Zhang. Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection. InECCV, 2024. 5, 19

    2024

  46. [46]

    RDT-1B: a diffusion foundation model for bimanual manipulation

    Songming Liu, Lingxuan Wu, Bangguo Li, Hengkai Tan, Huayu Chen, Zhengyi Wang, Ke Xu, Hang Su, and Jun Zhu. RDT-1B: a diffusion foundation model for bimanual manipulation. InICLR, 2025. 3 13 VoLo: A Physical Orchestrator for Open-VocabularyLong-Horizon Manipulation

    2025

  47. [47]

    Goal2Skill: Long-horizon manipulation with adaptive planning and reflection.arXiv preprint arXiv:2604.13942, 2026

    Zhen Liu, Xinyu Ning, Zhe Hu, Xinxin Xie, Weize Li, Zhipeng Tang, Chongyu Wang, Zejun Yang, Hanlin Wang, Yitong Liu, and Zhongzhu Pu. Goal2Skill: Long-horizon manipulation with adaptive planning and reflection.arXiv preprint arXiv:2604.13942, 2026. 2, 3

    Pith/arXiv arXiv 2026

  48. [48]

    Repo-vla: Recovery-driven policy optimization for vision-language-action models.arXiv preprint arXiv:2605.09410, 2026

    Weijia Liufu, Xiaoyu Guo, Ruiyi Chen, Jingzhi Liu, Kaidong Zhang, Xiwen Liang, Jianqi Lin, Dawei Sun, Yuze Wang, Rongtao Xu, Bingqian Lin, Bowen Yang, Tongtong Cao, Bowen Peng, Dongyu Zhang, Guangrun Wang, Min Wang, Liang Lin, and Xiaodan Liang. Repo-vla: Recovery-driven policy optimization for vision-language-action models.arXiv preprint arXiv:2605.09410...

    Pith/arXiv arXiv 2026

  49. [49]

    Generalvla: Generalizable vision– language–action models with knowledge-guided trajectory planning.arXiv preprint arXiv:2602.04315,

    Guoqing Ma, Siheng Wang, Zeyu Zhang, Shan Yu, and Hao Tang. Generalvla: Generalizable vision– language–action models with knowledge-guided trajectory planning.arXiv preprint arXiv:2602.04315,

    arXiv

  50. [50]

    CALVIN: A benchmark for language- conditioned policy learning for long-horizon robot manipulation tasks.IEEE Robotics and Automation Letters, 7(3):7327–7334, 2022

    Oier Mees, Lukas Hermann, Erick Rosete-Beas, and Wolfram Burgard. CALVIN: A benchmark for language- conditioned policy learning for long-horizon robot manipulation tasks.IEEE Robotics and Automation Letters, 7(3):7327–7334, 2022. 3

    2022

  51. [51]

    ReplanVLM: Replanning robotic tasks with visual language models.arXiv preprint arXiv:2407.21762, 2024

    Aoran Mei, Guo-Niu Zhu, Huaxiang Zhang, and Zhongxue Gan. ReplanVLM: Replanning robotic tasks with visual language models.arXiv preprint arXiv:2407.21762, 2024. 3

    arXiv 2024

  52. [52]

    Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning

    Mayank Mittal, Pascal Roth, James Tigue, Antoine Richard, Octi Zhang, Peter Du, Antonio Serrano-Muñoz, Xinjie Yao, René Zurbrügg, Nikita Rudin, et al. Isaac lab: A gpu-accelerated simulation framework for multi-modal robot learning.arXiv preprint arXiv:2511.04831, 2025. doi: 10.48550/arXiv.2511.04831. URLhttps://arxiv.org/abs/2511.04831. 4, 24

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2511.04831 2025

  53. [53]

    GraspGen: A diffusion-based framework for 6-DoF grasping with on-generator training.arXiv preprint arXiv:2507.13097, 2025

    Adithyavairavan Murali, Balakumar Sundaralingam, Yu-Wei Chao, Wentao Yuan, Jun Yamada, Mark Carlson, Fabio Ramos, Stan Birchfield, Dieter Fox, and Clemens Eppner. GraspGen: A diffusion-based framework for 6-DoF grasping with on-generator training.arXiv preprint arXiv:2507.13097, 2025. 5, 7, 19

    arXiv 2025

  54. [54]

    RoboCasa: Large-scale simulation of everyday tasks for generalist robots

    Soroush Nasiriany, Abhiram Maddukuri, Lance Zhang, Adeet Parikh, Aaron Lo, Abhishek Joshi, Ajay Mandlekar, and Yuke Zhu. RoboCasa: Large-scale simulation of everyday tasks for generalist robots. In Robotics: Science and Systems (RSS), 2024. 3

    2024

  55. [55]

    Closed loop interactive embodied reasoning for robot manipulation

    Michal Nazarczuk, Jan Kristof Behrens, Karla Stepanova, Matej Hoffmann, and Krystian Mikolajczyk. Closed loop interactive embodied reasoning for robot manipulation. InIEEE International Conference on Robotics and Automation (ICRA), 2025. 4

    2025

  56. [56]

    Kovalev, and Aleksandr I

    Svyatoslav Pchelintsev, Maxim Patratskiy, Anatoly Onishchenko, Alexandr Korchemnyi, Aleksandr Medvedev, Uliana Vinogradova, Ilya Galuzinsky, Aleksey Postnikov, Alexey K. Kovalev, and Aleksandr I. Panov. LERa: Replanning with visual feedback in instruction following.arXiv preprint arXiv:2507.05135,

    arXiv

  57. [57]

    FAST: Efficient action tokenization for vision-language-action models.arXiv preprint arXiv:2501.09747, 2025

    Karl Pertsch, Kyle Stachowicz, Brian Ichter, Danny Driess, Suraj Nair, Quan Vuong, Oier Mees, Chelsea Finn, and Sergey Levine. FAST: Efficient action tokenization for vision-language-action models.arXiv preprint arXiv:2501.09747, 2025. 7

    Pith/arXiv arXiv 2025

  58. [58]

    Belinda Phipson and Gordon K. Smyth. Permutation p-values should never be zero: calculating exact p-values when permutations are randomly drawn.Statistical Applications in Genetics and Molecular Biology, 9(1):Article 39, 2010. 29

    2010

  59. [59]

    SAM 2: Segment anything in images and videos.arXiv preprint arXiv:2408.00714, 2024

    Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman Rädle, Chloe Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross Girshick, Piotr Dollár, and Christoph Feichtenhofer. SAM 2: Segment anything in images and videos.arXiv preprint arXiv:2408.007...

    Pith/arXiv arXiv 2024

  60. [60]

    Hierarchical vision-language planning for multi-step humanoid manipulation

    André Schakkal, Ben Zandonati, Zhutian Yang, and Navid Azizan. Hierarchical vision-language planning for multi-step humanoid manipulation. InRobotics: Science and Systems (RSS) Workshop on Robot Planning in the Era of Foundation Models, 2025. arXiv:2506.22827. 3

    arXiv 2025

  61. [61]

    TiPToP: A modular open-vocabulary planning system for robotic manipulation.arXiv preprint arXiv:2603.09971, 2026

    William Shen, Nishanth Kumar, Sahit Chintalapudi, Jie Wang, Christopher Watson, Edward Hu, Jing Cao, Dinesh Jayaraman, Leslie Pack Kaelbling, and Tomás Lozano-Pérez. TiPToP: A modular open-vocabulary planning system for robotic manipulation.arXiv preprint arXiv:2603.09971, 2026. 3, 7

    arXiv 2026

  62. [62]

    Memoryvla: Perceptual-cognitive memory in vision-language-action models for robotic manipulation

    Hao Shi, Bin Xie, Yingfei Liu, Lin Sun, Fengrong Liu, Tiancai Wang, Erjin Zhou, Haoqiang Fan, Xi- angyu Zhang, and Gao Huang. Memoryvla: Perceptual-cognitive memory in vision-language-action models for robotic manipulation. InInternational Conference on Learning Representations (ICLR), 2026. arXiv:2508.19236. 3

    Pith/arXiv arXiv 2026

  63. [63]

    Hi robot: Open-ended instruction following with hierarchical vision-language-action models.arXiv preprint arXiv:2502.19417, 2025

    Lucy Xiaoyang Shi, Brian Ichter, Michael Equi, Liyiming Ke, Karl Pertsch, Quan Vuong, James Tanner, Anna Walling, Haohuan Wang, Niccolo Fusai, Adrian Li-Bell, Danny Driess, Lachy Groom, Sergey Levine, and Chelsea Finn. Hi robot: Open-ended instruction following with hierarchical vision-language-action models.arXiv preprint arXiv:2502.19417, 2025. 2, 3

    Pith/arXiv arXiv 2025

  64. [64]

    ProgPrompt: Generating situated robot task plans using large language models

    Ishika Singh, Valts Blukis, Arsalan Mousavian, Ankit Goyal, Danfei Xu, Jonathan Tremblay, Dieter Fox, Jesse Thomason, and Animesh Garg. ProgPrompt: Generating situated robot task plans using large language models. InICRA, 2023. 2, 3

    2023

  65. [65]

    RePLan: Robotic replanning with perception and language models.arXiv preprint arXiv:2401.04157, 2024

    Marta Skreta, Zihan Zhou, Jia Lin Yuan, Kourosh Darvish, Alán Aspuru-Guzik, and Animesh Garg. RePLan: Robotic replanning with perception and language models.arXiv preprint arXiv:2401.04157, 2024. 3

    arXiv 2024

  66. [66]

    ManiSkill3: GPU parallelized robotics simulation and rendering for generalizable embodied AI.arXiv preprint arXiv:2410.00425, 2024

    Stone Tao, Fanbo Xiang, Arth Shukla, Yuzhe Qin, Xander Hinrichsen, Xiaodi Yuan, Chen Bao, Xinsong Lin, Yulin Liu, Tse-kai Chan, Yuan Gao, Xuanlin Li, Tongzhou Mu, Nan Xiao, Arnav Gurha, Zhiao Huang, Roberto Calandra, Rui Chen, Shan Luo, and Hao Su. ManiSkill3: GPU parallelized robotics simulation and rendering for generalizable embodied AI.arXiv preprint ...

    arXiv 2024

  67. [67]

    Edwin B. Wilson. Probable inference, the law of succession, and statistical inference.Journal of the American Statistical Association, 22(158):209–212, 1927. 30

    1927

  68. [68]

    Hivla: A visual-grounded-centric hierarchical embodied manipulation system.arXiv preprint arXiv:2604.14125, 2026

    Tianshuo Yang, Guanyu Chen, Yutian Chen, Zhixuan Liang, Yitian Liu, Zanxin Chen, Chunpu Xu, Haotian Liang, Jiangmiao Pang, Yao Mu, and Ping Luo. Hivla: A visual-grounded-centric hierarchical embodied manipulation system.arXiv preprint arXiv:2604.14125, 2026. 3

    Pith/arXiv arXiv 2026

  69. [69]

    RoboLab: A high-fidelity simulation benchmark for analysis of task generalist policies

    Xuning Yang, Rishit Dagli, Alex Zook, Hugo Hadfield, Ankit Goyal, Stan Birchfield, Fabio Ramos, and Jonathan Tremblay. RoboLab: A high-fidelity simulation benchmark for analysis of task generalist policies. RSS, 2026. 2, 3, 4, 6, 24, 34

    2026

  70. [70]

    Fpc-vla: A vision-language-action framework with a supervisor for failure prediction and correction.Expert Systems with Applications, 316:131742,

    Yifan Yang, Zhixiang Duan, Tianshi Xie, Fuyu Cao, Pinxi Shen, Peili Song, Chenyang Zhao, Piaopiao Jin, Guokang Sun, Shaoqing Xu, Yangwei You, and Jingtai Liu. Fpc-vla: A vision-language-action framework with a supervisor for failure prediction and correction.Expert Systems with Applications, 316:131742,

  71. [71]

    Agentic robot: A brain-inspired framework for vision-language- action models in embodied agents.arXiv preprint arXiv:2505.23450, 2025

    Zhejian Yang, Yongchao Chen, Xueyang Zhou, Jiangyue Yan, Dingjie Song, Yinuo Liu, Yuting Li, Yu Zhang, Pan Zhou, Hechang Chen, and Lichao Sun. Agentic robot: A brain-inspired framework for vision-language- action models in embodied agents.arXiv preprint arXiv:2505.23450, 2025. 2, 3

    arXiv 2025

  72. [72]

    Guiding long-horizon task and motion planning with vision language models.arXiv preprint arXiv:2410.02193,

    Zhutian Yang, Caelan Garrett, Dieter Fox, Tomás Lozano-Pérez, and Leslie Pack Kaelbling. Guiding long-horizon task and motion planning with vision language models.arXiv preprint arXiv:2410.02193,

    arXiv

  73. [73]

    3 15 VoLo: A Physical Orchestrator for Open-VocabularyLong-Horizon Manipulation

  74. [74]

    World action models are zero-shot policies.arXiv preprint arXiv:2602.15922, 2026

    Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng, Shenyuan Gao, Sihyun Yu, George Kurian, Suneel Indupuru, You Liang Tan, Chuning Zhu, Jiannan Xiang, Ayaan Malik, Kyungmin Lee, William Liang, Nadun Ranawaka, Jiasheng Gu, Yinzhen Xu, Guanzhi Wang, Fengyuan Hu, Avnish Narayan, Johan Bjorck, Jing Wang, Gwanghyun Kim, Dantong Niu, Ruijie Zheng, Yuqi Xie, Jimmy Wu, Qi ...

    Pith/arXiv arXiv 2026

  75. [75]

    RoboFAC: A compre- hensive framework for robotic failure analysis and correction.arXiv preprint arXiv:2505.12224, 2025

    Zewei Ye, Weifeng Lu, Minghao Ye, Tao Lin, Shuo Yang, Junchi Yan, and Bo Zhao. RoboFAC: A compre- hensive framework for robotic failure analysis and correction.arXiv preprint arXiv:2505.12224, 2025. 3

    arXiv 2025

  76. [76]

    Critic in the loop: A tri-system VLA framework for robust long-horizon manipulation.arXiv preprint arXiv:2603.05185,

    Pengfei Yi, Yingjie Ma, Wenjiang Xu, Yanan Hao, Shuai Gan, Wanting Li, and Shanlin Zhong. Critic in the loop: A tri-system VLA framework for robust long-horizon manipulation.arXiv preprint arXiv:2603.05185,

    arXiv

  77. [77]

    HiRT: Enhancing robotic control with hierarchical robot transformers

    Jianke Zhang, Yanjiang Guo, Xiaoyu Chen, Yen-Jen Wang, Yucheng Hu, Chengming Shi, and Jianyu Chen. HiRT: Enhancing robotic control with hierarchical robot transformers. InCoRL, 2024. 3

    2024

  78. [78]

    VLABench: A large-scale benchmark for language-conditioned robotics manipulation with long-horizon reasoning tasks.arXiv preprint arXiv:2412.18194, 2024

    Shiduo Zhang, Zhe Xu, Peiju Liu, Xiaopeng Yu, Yuan Li, Qinghui Gao, Zhaoye Fei, Zhangyue Yin, Zuxuan Wu, Yu-Gang Jiang, and Xipeng Qiu. VLABench: A large-scale benchmark for language-conditioned robotics manipulation with long-horizon reasoning tasks.arXiv preprint arXiv:2412.18194, 2024. 3, 31, 32

    arXiv 2024

  79. [79]

    Closed-loop open-vocabulary mobile manipulation with GPT-4V

    Peiyuan Zhi, Zhiyuan Zhang, Yu Zhao, Muzhi Han, Zeyu Zhang, Zhitian Li, Ziyuan Jiao, Baoxiong Jia, and Siyuan Huang. Closed-loop open-vocabulary mobile manipulation with GPT-4V. InICRA, 2025. 3, 4

    2025

  80. [80]

    Action-primitive pipelines

    Yuke Zhu, Josiah Wong, Ajay Mandlekar, Roberto Martín-Martín, Abhishek Joshi, Kevin Lin, Abhiram Maddukuri, Soroush Nasiriany, and Yifeng Zhu. robosuite: A modular simulation framework and benchmark for robot learning.arXiv preprint arXiv:2009.12293, 2020. 2, 3 16 VoLo: A Physical Orchestrator for Open-VocabularyLong-Horizon Manipulation Appendix We provi...

    Pith/arXiv arXiv 2009

Showing first 80 references.