DexHoldem: Playing Texas Hold'em with Dexterous Embodied System

Hugging Face Daily Papers Papers
dexterous-manipulation embodied-agents benchmark texas-holdem shadowhand teleoperation perception

Summary

DexHoldem is a real-world benchmark for evaluating embodied agents in dexterous manipulation tasks, using Texas Hold'em with a ShadowHand to test primitive execution, perception, and decision-making in a closed-loop setting.

Evaluating embodied systems on real dexterous hardware requires more than isolated primitive skills: an agent must perceive a changing tabletop scene, choose a context-appropriate action, execute it with a dexterous hand, and leave the scene usable for later decisions. We introduce DexHoldem, a real-world system-level benchmark built around Texas Hold'em dexterous manipulation with a ShadowHand. DexHoldem provides 1,470 teleoperated demonstrations across 14 Texas Hold'em manipulation primitives, a standardized physical policy benchmark, and an agentic perception benchmark that tests whether agents can recover the structured game state needed for embodied decision making. On primitive execution, π_{0.5} obtains the highest task completion rate (61.2%), while π_{0.5} and π_0 tie on scene-preserving success rate (47.5%). On agentic perception, Opus 4.7 obtains the best strict problem-level accuracy (34.3%), while GPT 5.5 obtains the best average field-wise accuracy (66.8%), exposing a gap between isolated visual sub-capabilities and complete routing-relevant state recovery. Finally, we instantiate the full embodied-agent loop in three case studies, where waiting, recovery dispatches, human-help requests, and repeated primitive execution reveal how perception and policy errors accumulate during closed-loop deployment. DexHoldem therefore evaluates dexterous tabletop execution, agentic perception, and embodied decision routing in a shared physical setting. Project page: https://dexholdem.github.io/Dexholdem/.
Original Article
View Cached Full Text

Cached at: 05/19/26, 10:34 PM

Paper page - DexHoldem: Playing Texas Hold’em with Dexterous Embodied System

Source: https://huggingface.co/papers/2605.18727

Abstract

DexHoldem presents a real-world benchmark for evaluating embodied agents in dexterous manipulation tasks, testing both primitive execution and higher-level perception and decision-making capabilities.

Evaluatingembodied systemson real dexterous hardware requires more than isolated primitive skills: an agent must perceive a changing tabletop scene, choose a context-appropriate action, execute it with a dexterous hand, and leave the scene usable for later decisions. We introduce DexHoldem, a real-world system-level benchmark built around Texas Hold’emdexterous manipulationwith aShadowHand. DexHoldem provides 1,470teleoperated demonstrationsacross 14 Texas Hold’em manipulation primitives, a standardizedphysical policy benchmark, and anagentic perceptionbenchmark that tests whether agents can recover the structured game state needed for embodied decision making. On primitive execution, π_{0.5} obtains the highesttask completion rate(61.2%), while π_{0.5} and π_0 tie onscene-preserving success rate(47.5%). Onagentic perception, Opus 4.7 obtains the beststrict problem-level accuracy(34.3%), while GPT 5.5 obtains the bestaverage field-wise accuracy(66.8%), exposing a gap between isolated visual sub-capabilities and complete routing-relevant state recovery. Finally, we instantiate the fullembodied-agent loopin three case studies, where waiting, recovery dispatches, human-help requests, and repeated primitive execution reveal how perception and policy errors accumulate duringclosed-loop deployment. DexHoldem therefore evaluates dexterous tabletop execution,agentic perception, and embodied decision routing in a shared physical setting. Project page: https://dexholdem.github.io/Dexholdem/.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2605\.18727

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.18727 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.18727 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.18727 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles