paper-with-me

홈 › Papers

Show-Harness: Just a VLM Agent Can Play Robots

2026-09-09 · Yanzhe Chen, Zechen Bai, Zhijun Cao, Wenzheng Zeng, Kevin Qinghong Lin, Yiqi Lin, Guoqiang Liang, Kevin Yuchen Ma, Qiming Huang, Mike Zheng Shou arxiv

Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence into robot control remains challenging. We present Show-Harness, an Embodied Harness that enables VLMs to "play" robots through a compact semantic interface linking intent to action. Show-Harness exposes discrete semantic action units that VLMs can naturally reason over, while embodiment-specific interpreters deterministically ground them into local robot actions, keeping the VLM directly responsible for fine-grained physical decisions. Through the same interface, Show-Harness demonstrates the feasibility of (1) directly unlocking closed-source frontier VLMs for zero-shot robot control, and (2) adapting small-scale open-source VLMs for low-cost deployment with just a few GPU-hours of fine-tuning. We further develop GUMI (GUI Manipulation Interface), which extends the same semantic action space to GUI-based demonstration collection, allowing humans and agents to "play" robots across embodiments without specialized teleoperation hardware. Extensive experiments show that Show-Harness-equipped VLM agents generalize robustly across tasks, embodiments, and environments, outperforming representative agentic and VLA paradigms. These results suggest that the right interface can unlock substantial embodied capability from foundation VLMs, without requiring additional model capacity or costly embodiment-specific pretraining.

📄 PDF Abstract BibTeX arXiv:2609.10522

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AutoHarness: improving LLM agents by automatically synthesizing a code harness

2026-02-10 · Xinghua Lou, Miguel Lázaro-Gredilla, Antoine Dedieu, Carter Wendelken 외 arxiv

Despite significant strides in language models in the last few years, when used as agents, such models often try to perform actions that are not just suboptimal for a given state, but are strictly prohibited by the exter…

Decision Making

Nautilus: From One Prompt to Plug-and-Play Robot Learning

2026-05-12 · Yufeng Jin, Jianfei Guo, Xiaogang Jia, Yu Deng 외 arxiv

Robot learning research is fragmented across policy families, benchmark suites, and real robots; each implementation is entangled with the others in a complex combination matrix, making it an engineering nightmare to por…

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

2026-08-26 · Guibin Zhang, Leo Lu, Fangzhou Xie, Kang Zhu 외 arxiv

Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can dominate the contribution of the underlying …

Mutual Alignment Transfer Learning

2017-07-25 · Markus Wulfmeier, Ingmar Posner, Pieter Abbeel

Training robots for operation in the real world is a complex, time consuming and potentially expensive task. Despite significant success of reinforcement learning in games and simulations, research in real robot applicat…

Reinforcement LearningTransfer Learning

PTCG-Bench: Can LLM Agents Master Pokémon Trading Card Game?

2026-05-28 · Dongdong Hua, Yifei Sun, Renhong Huang, Feng Gao 외 arxiv

Given a strategically complex board game, human players can quickly learn to devise strategies after playing a few rounds. Autonomous agents require similar capabilities in realistic interactive environments, yet existin…