The paper introduces RESCUE, a counterfactual framework that evaluates whether runtime monitors for robot policies generate alarms that lead to useful interventions. By restoring simulator and policy states at checkpoints, RESCUE compares alternative actions to identify the latest checkpoint that satisfies a recovery criterion and measures whether acting on alarms reduces expected task‑completion cost. Experiments on OpenVLA‑OFT and π0.5 over LIBERO‑Spatial and LIBERO‑Plus show that recoverability depends on the state–intervention pair, and that even an ideal detector can only tolerate a 2.0–3.3% false‑alarm rate before unnecessary resets outweigh early failure stops.
By David Ahmedt-Aristizabal, Abdelwahed Khamis, Mohammad Ali Armin, Lars Petersson
IndustrialVLA-Bench evaluates six released vision‑language‑action (VLA) and world‑action (WAM) robot policy models using a unified reporting schema. It measures clean capability on LIBERO, non‑language robustness on LIBERO‑Plus, instruction sensitivity on LIBERO‑Para, and observed execution cost, aggregating results across three random seeds. The benchmark also reports inference latency, peak memory, runtime mode, and evidence status for each system, enabling traceable comparisons without claiming one paradigm is universally superior.
By Yiqi Wang, Zhifeng Rao, Jiaqi Zhang, Xiaoyang Li, Zhangkai Wu, Yiqun Duan, Mingkai Zheng, Fei Wang, Shan You, Taotao Cai
arXiv:2606. 03134v1 Announce Type: cross Abstract: Imitation-learning policies for robot manipulation inherit the quality of the success labels attached to their training episodes, and those labels are usually produced by the robot's own success check.
By Aarav Bedi (University of California, Berkeley)
Traceable World State (TWS) is a middleware‑neutral semantic representation that records robotic world states with provenance, including entities, relations, observations, confidence, and revision metadata. TWS snapshots are immutable, support deterministic replay through ordered updates, and use a SHA‑256 hash chain for tamper‑evident logging. Evaluation on Python 3.10‑3.14, BEHAVIOR‑1K tasks, and simulated NVIDIA Unitree G1 trajectories shows TWS passes 38 tests, validates complete state lifecycles, achieves exact terminal‑state replay, and detects all injected corruptions with only a 1.72% storage overhead over plain JSONL.
By Zoe Li
arXiv:2607. 23532v1 Announce Type: cross Abstract: Swarms of LLM-assisted autonomous robots are increasingly proposed for cooperative intelligence, surveillance, and reconnaissance (ISR) in contested environments.
By Nikolaos Kekatos, Stylianos Basagiannis, Panagiotis Katsaros, Alexios Lekidis, Tom Nianios
arXiv:2610.14530v1 Announce Type: cross
Abstract: Multi-robot systems (MRS) offer significant advantages over single-robot platforms by enabling information sharing and coordination for different tas...
By Ruiyang Wang, Hao-Lun Hsu, Haocheng Meng, Songqiao Xie, Miroslav Pajic