cs.RO · 2026-10-02 · No. 131

Robotics, 2026-10-02.

7 new papers in cs.RO. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

7 entries
  1. 01

    Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents

    Yen-Jen Wang, Haozhe Jiang, Shuying Deng, Haoru Xue, Weirui Ye, Rocky Duan, Nika Haghtalab, S. Shankar Sastry,...

    cs.RO · cs.AI · eess.SY

    Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perception with control. We present Reconstruct, Practice, Go Real (RPG), a framework for autonomous improvement of robot execution systems without updating model weights. RPG identifies manipulation capabilities in an offline dataset and constructs related practice tasks in simulation....

    arxiv.org/abs/2610.02204 · PDF

  2. 02

    Watch, Infer, Coordinate: Inferring Robot Partner Constraints for Zero-Shot Coordination

    Suyu Ye, Zheyuan Zhang, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Tianmin Shu, Homanga...

    cs.RO · cs.AI · cs.MA

    Robots operating in the physical world will increasingly need to coordinate with other robots, particularly in manipulation tasks where an object may be too large or heavy for a single robot to carry alone. Physical limitations caused by hardware degradation or actuator faults can restrict the actions a robot can reliably execute, yet these limitations may be unknown to its partner. We study whether a helper can infer a robot partner's...

    arxiv.org/abs/2610.02170 · PDF

  3. 03

    DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication

    Hanchu Zhou, Dechen Gao, Hang Wang, Brendan Lynch, Boqi Zhao, Qiyao Ma, Raman Goyal, Junshan Zhang

    cs.RO · cs.AI

    Vision-language models (VLMs) and vision-language-action models (VLAs) have recently driven rapid progress in general-purpose robots, yet most progress has focused on single-robot settings. Extending these capabilities to multi-robot systems remains challenging because robots must coordinate long-horizon behaviors while maintaining reliable, fine-grained execution. We introduce DuoMind, a distributed hierarchical framework for multi-robot...

    arxiv.org/abs/2610.02161 · PDF

  4. 04

    HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution

    Kyochul Jang, Seohyeon Park, Ohchul Kwon, Sangjun Park, Junhyeok Choi, Seungyeop Yi, Chaeyun Kim, Sangkyu Lee, Idan...

    cs.RO · cs.AI

    As robotic hardware and learning methods advance, humanoids need tools to perform tasks beyond their inherent physical limits. Successful tool use requires selecting a suitable tool and coordinating manipulation and, when needed, locomotion to complete the task. Existing benchmarks do not jointly evaluate these capabilities on a humanoid. We introduce HumanoidToolBench, an 18-task benchmark spanning three scenarios, three execution levels,...

    arxiv.org/abs/2610.02089 · PDF

  5. 05

    Training-Free Diffusion Planning with Analytical Local Scores

    Michael Y. Fatemi, Jinhao Liang, Ferdinando Fioretto

    cs.RO · cs.LG

    Path finding and multi-robot motion planning require trajectories that are smooth, goal-directed, and collision-free in environments with complex geometric constraints. Recent diffusion-based planners have shown that trajectory generation can be cast as iterative denoising which has opened the doors to learning-based approaches that can handle multi-modal trajectory distributions and refine entire trajectories. However, a key limitation is...

    arxiv.org/abs/2610.01959 · PDF

  6. 06

    End-to-End Learning vs. Modular Architectures: Comparative Insights into Autonomous Driving Systems

    Kartik B. Kapse

    cs.RO · cs.CV · cs.LG

    Autonomous driving systems have become a central focus of intelligent transportation research, with End-to-End Learning and Modular Architectures offering two prominent design paradigms for their implementation. E2E Learning uses deep learning algorithms to map raw sensory inputs directly to driving actuators, providing a streamlined and adaptable solution. while Modular Architectures employ a pipeline-based approach, dividing the system into...

    arxiv.org/abs/2610.01746 · PDF

  7. 07

    Completion Aware Guidance for World Action Models

    Seungyeon Kim, Junhoo Lee, Baekseung Kim, Minkyu Kim, Nojun Kwak

    cs.RO · cs.AI · cs.LG

    World Action Models (WAMs) predict visual futures and robot actions, yet they remain susceptible to task-incomplete imagination, where plausible, action-consistent predictions omit the transition needed for task completion. In this paper, we show that this failure is not inherent to the world model backbone, but emerges when adapted for short-chunk control, which can repeatedly favor plausible local continuations over task-completing...

    arxiv.org/abs/2610.01559 · PDF

This edition is part of The Daily Abstract — cs.RO archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.