Guava: An Effective and Universal Harness for Embodied Manipulation

• URL: http://arxiv.org/abs/2606.18363v1
• Date: Tue, 16 Jun 2026 18:09:26 GMT
• Title: Guava: An Effective and Universal Harness for Embodied Manipulation
• Abstract summary: We develop an end-to-end training pipeline that distills embodied manipulation capabilities into a 4B open-source model.<n>Results suggest that a well-designed harness can serve as a scalable, model-agnostic interface for embodied manipulation.
• Score: 74.34187069605844
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through embodied tools use offers a promising alternative to end-to-end vision-language-action systems by combining high-level reasoning with external modules for perception, planning, and control. However, it remains unclear what makes an effective harness for embodied manipulation, and to what extent such a harness can unlock embodied capabilities in a wide range of reasoning models. In this work, we present Guava, a harness framework for embodied tool use developed through systematic exploration of the design space of agent workflows, action spaces, and observation spaces. Our study identifies three key ingredients for effective embodied agents: iterative perception-reasoning-action loops, semantic action abstractions, and multimodal observations. To understand whether these design principles are universal even to small models, we develop an end-to-end training pipeline that distills embodied manipulation capabilities into a 4B open-source model using fewer than 2K trajectories collected entirely in simulation. Experimental results in both simulation and real-world environments show performance comparable to frontier proprietary models while exhibiting strong generalization to unseen objects, novel instructions, and long-horizon tasks. Results suggest that a well-designed harness can serve as a scalable, model-agnostic interface for embodied manipulation, enabling strong emergent embodied capabilities in compact open-source models with minimal training data.

Related papers

• Real-World Cooperative Bimanual Dexterous Grasp of Large Objects from Single-View Observations [18.70687400045831]
  Bimanual dexterous grasping of large objects is a critical challenge in robotic manipulation.<n>We propose a real-world bimanual grasping framework that includes a multimodal dataset capturing joint angles, visual observations and force signals.<n>Our approach enables the synthesis of executable bimanual grasps from single-view inputs, reducing dependence on complete 3D object models.
  arXiv  Detail & Related papers  (2026-08-11T02:24:27Z)
• From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence [54.62791372989525]
  Action models, vision-language--action policies, and world models have advanced this goal.<n>World Action Models (WAMs) are particularly promising because they connect candidate interventions with predicted consequences.<n>We review the evolution toward WAMs and organize these limitations into three coupled gaps: model roles and representations, objectives and standardization, and system composition.
  arXiv  Detail & Related papers  (2026-07-13T15:22:56Z)
• HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents [71.09493646932046]
  We introduce HY-Embodied-0.5, a family of foundation models specifically designed for real-world embodied agents.<n>The HY-Embodied-0.5 suite comprises two primary variants: an efficient model with 2B activated parameters designed for edge deployment, and a powerful model with 32B activated parameters targeted for complex reasoning.<n>Our MoT-2B model outperforms similarly sized state-of-the-art models on 16 benchmarks, while the 32B variant achieves performance comparable to frontier models such as Gemini 3.0 Pro.
  arXiv  Detail & Related papers  (2026-04-08T17:59:48Z)
• Beyond Language Modeling: An Exploration of Multimodal Pretraining [125.34714978184638]
  We provide empirical clarity through controlled, from-scratch pretraining experiments.<n>We adopt the Transfusion framework, using next-token prediction for language and diffusion for vision.<n>We demonstrate that the MoE architecture harmonizes this scaling asymmetry by providing the high model capacity required by language.
  arXiv  Detail & Related papers  (2026-03-03T18:58:00Z)
• Flow Battery Manifold Design with Heterogeneous Inputs Through Generative Adversarial Neural Networks [0.0]
  We introduce a systematic framework for constructing training datasets tailored to generative models.<n>We show how integrating generative models with Bayesian optimization can enhance the interpretability of the latent space of admissible designs.<n>This work broadens the applicability of generative machine-learning models in system designs by enhancing quality and reliability.
  arXiv  Detail & Related papers  (2025-08-12T11:40:09Z)
• Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments [70.42705564227548]
  We propose an automated environment construction pipeline for large language models (LLMs)<n>This enables the creation of high-quality training environments that provide detailed and measurable feedback without relying on external tools.<n>We also introduce a verifiable reward mechanism that evaluates both the precision of tool use and the completeness of task execution.
  arXiv  Detail & Related papers  (2025-08-12T09:45:19Z)
• Activation Space Interventions Can Be Transferred Between Large Language Models [0.5541644538483947]
  We show that safety interventions can be transferred between models through learned mappings of their shared activation spaces.<n>We demonstrate this approach on two well-established AI safety tasks: backdoor removal and refusal of harmful prompts.<n>We also propose a new task, textitcorrupted capabilities, where models are fine-tuned to embed knowledge tied to a backdoor.
  arXiv  Detail & Related papers  (2025-03-06T13:38:44Z)
• AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO [0.0]
  Large Language Models (LLMs) have demonstrated impressive capabilities in language processing, yet they often struggle with tasks requiring visual spatial reasoning.<n>We introduce a novel two-stage training framework designed to equip standard LLMs with visual reasoning abilities for maze navigation.
  arXiv  Detail & Related papers  (2025-02-20T16:05:18Z)
• LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models [50.259006481656094]
  We present a novel interactive application aimed towards understanding the internal mechanisms of large vision-language models. Our interface is designed to enhance the interpretability of the image patches, which are instrumental in generating an answer. We present a case study of how our application can aid in understanding failure mechanisms in a popular large multi-modal model: LLaVA.
  arXiv  Detail & Related papers  (2024-04-03T23:57:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.