cs.RO · 2026-10-13 · No. 142

Robotics, 2026-10-13.

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

01 — The papers

8 entries
  1. 01

    MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents

    Jingwei Song, Zhisheng Chen, Bingfan Zeng, Jing Tang, Yubo Hou, Jinhao Jing, Zhengwei Xie, Linfeng Zhang

    cs.RO · cs.AI

    A central challenge in embodied recursive self-improvement is enabling agents to convert interaction history into capabilities that persist beyond one world and transfer to later tasks. A saved memory or successful final action does not by itself establish that a reusable capability was acquired; evaluation must separate capability change from carried-over resources, unequal source exposure, and early execution failures. We construct...

    arxiv.org/abs/2610.13829 · PDF

  2. 02

    Dream to Remember: Continual Steering of Generalist Robot Policies with World Models

    Bahey Tharwat, Iman Nematollahi, Marvin Alles, Xingyuan Zhang, Akshay L Chandra, Abhinav Valada

    cs.RO · cs.CV · cs.LG

    Generalist robot policies are trained with imitation learning and are bounded by the quality and coverage of their demonstrations. Reinforcement learning can improve and extend them, either by fine-tuning the policy weights or by training a small module to steer the input noise of a frozen generative policy. When tasks arrive sequentially, both approaches suffer from catastrophic forgetting. Fine-tuning on a task degrades prior tasks, and...

    arxiv.org/abs/2610.13816 · PDF

  3. 03

    SmolWAM: A Latent World-Action Model for Robotic Manipulation on Edge Devices

    Timi Owolabi, Hikmah Olawore, Frances Adelakun, Ayotomiwa Oyewumi

    cs.RO · cs.LG

    World-action models (WAMs) predict a robot's actions together with the observations those actions will produce. However, the strongest models rely on video diffusion transformers that are far too computationally expensive for resource-constrained edge devices. We present SmolWAM, a latent WAM that we derive from the 2B-parameter Cosmos Policy by keeping its pretrained trunk and rebuilding its inference interface: single-frame visual latents,...

    arxiv.org/abs/2610.13740 · PDF

  4. 04

    JitterVLA: A Replay Benchmark for Motion Quality in VLA-Driven Human-Robot Manipulation

    Faith Ogunwoye, Didar Seyidov, Konstantin Gubernatorov, Dzmitry Tsetserukou

    cs.RO · cs.HC · cs.LG

    Vision-language-action (VLA) policies issue sparse targets whose arrival at the robot controller is delayed and irregular, so a reasonable predicted action can still produce abrupt motion near people. Remedies are evaluated on different streams, delays and metrics. JitterVLA replays identical commands and arrival traces through alternative controllers, isolating the controller's effect. We apply it to synthetic reaches, hand trajectories from...

    arxiv.org/abs/2610.13628 · PDF

  5. 05

    RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation

    Xuhui Kang, Sung-Wook Lee, Yan Zhuang, Tianle Zhong, Yen-Ling Kuo

    cs.RO · cs.CV · cs.LG

    Pre-trained robot policies, such as Vision-Language-Action (VLA) models, provide a strong foundation for generalist robotic manipulation, but adapting them to new tasks with only a few demonstrations remains challenging. Directly fine-tuning a pre-trained policy often achieves strong in-distribution performance, yet it can distort the representations learned during pre-training and weaken the model's generalization ability under...

    arxiv.org/abs/2610.13578 · PDF

  6. 06

    RESCUE: Is This Alarm Worth Acting On? Counterfactual Evaluation of VLA Runtime Monitors

    David Ahmedt-Aristizabal, Abdelwahed Khamis, Mohammad Ali Armin, Lars Petersson

    cs.RO · cs.AI

    Runtime failure monitors for robot policies are typically evaluated by how accurately they distinguish failed from successful executions. Yet an accurate alarm may arrive too late for recovery, while an unnecessary intervention may disrupt an execution that would otherwise succeed. We introduce RESCUE, a counterfactual framework for evaluating whether a monitor's alarms enable useful interventions. By restoring simulator and policy states at...

    arxiv.org/abs/2610.13516 · PDF

  7. 07

    Beyond Actions: Learning Future Operation Targets for Vision-Language-Action Models

    Min Lin, Bokai Zhou, Jianqi Lin, Kaiyuan Yang, Yicheng Chang, Junjie Yu, Xiaofan Liu, Jianhua Han, Rui Li, Shen...

    cs.RO · cs.AI

    Actions specify what a robot should execute, but do not describe what those commands will achieve. Vision-language-action (VLA) policies nevertheless learn primarily by predicting action chunks from images, language, and state. We introduce Action--Future Coupled Effect Learning (AFCE), which makes a future-grounded physical Effect the policy's primary prediction target. An offline tokenizer constructs temporally ordered Effect tokens from...

    arxiv.org/abs/2610.13212 · PDF

  8. 08

    Prediction-Informed Landing Window Planning for UAV Landing on USV in High Sea States

    Kaizhen Li, Xi Zhou, Dan Zhang, Xiaowei Li

    cs.RO · cs.LG

    Autonomous landing of unmanned aerial vehicle (UAV) on unmanned surface vehicle (USV) is difficult in high sea states. Existing hierarchical landing methods often infer future USV motion only implicitly from short observation histories, which limits their ability to adapt to severe and rapidly changing sea conditions. This paper presents a prediction-informed hierarchical control framework. A pretrained model is developed to explicitly...

    arxiv.org/abs/2610.13190 · 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.