This work introduces RobotAgentBench (RAB), a comprehensive benchmark for evaluating robot agents in realistic, open-world household environments and enables systematic comparisons of standalone VLA/WAM models and diverse robot agent architectures under a unified planning-execution-verification framework.
Ling-Jun Mao, Jing-Lin Cao, Lu-Kun He et al.· 1 citation
Backdoor-defense leaderboards print a clean-accuracy drop and read it as removal cost. Measured on the poisoned victim alone, the drop cannot separate removal from what the defense does to any model, and inherits the victim's start, which for three of BackdoorBench's sixteen attacks is a configuration file: WaNet, BPP...
RSIAgent is introduced, a training-free multi-agent framework for recursive self-improvement through autonomous memory construction that substantially improves strong open-source models, enabling Kimi-K3 and GLM-5.3 to outperform frontier closed-source models including GPT-6.3.
Si-Bo Zhu, Shi-Cheng Fan, Xin-Yue Wang et al.· 10 citations
This paper presents StructAgent, a state-centered framework that introduces a unified state for maintaining compact, verifiable task progress and a structured workflow that regulates progress through verifier-backed state transitions and generalizes beyond desktop environments to Minecraft, demonstrating the generality...
Wenyi Wu, Sibo Zhu, Kun Zhou et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.