cs.RONov 18, 2026

Grana: Compositional Reward Modeling for Long-Horizon Robot Manipulation

Authors: Zi-ang Cao, Kaiyuan Zheng, Yinzhen Xu, Haonan Duan, Jiasheng Gu, Fengyuan Hu, Nan Zhu, Kun Lei, 

Organizations: NVIDIA · The University of Texas at Austin · University of Washington

Abstract

Robot reward modeling faces two challenges: generalizing across tasks and accurately tracking progress in long-horizon manipulation. General-purpose reward models demonstrate broad task transfer, but transfer from short-task pretraining to long-horizon tasks remains underexplored. Long-horizon progress models often rely on task-specific subtask classifiers or fixed action vocabularies, limiting the reuse of learned progress knowledge when adapting to new tasks. To address these challenges, we introduce Grana, a vision-language robot reward model that learns to identify unfinished subtasks and estimate their continuous progress using open-vocabulary subtask descriptions. We train a language-conditioned model to estimate progress in short-horizon tasks and individual subtasks of long-horizon tasks. For long-horizon tasks, we combine the selected subtask's predicted progress with credit for preceding completed subtasks to estimate whole-task progress. General progress prediction requires training the model across diverse tasks with progress supervision that accounts for imperfect execution. Elapsed-time proxies can misrepresent progress when relative subtask durations vary, or failures reverse local progress. We therefore introduce an annotation protocol that converts sparse subtask boundaries and action-quality annotations into dense progress targets, without requiring annotators to assign numerical progress scores. Pretraining with this supervision on 200 diverse, mostly short-horizon manipulation tasks enables zero-shot reward prediction on unseen tasks and improves progress prediction after adaptation to multi-minute, long-horizon tasks. Experiments demonstrate (i) generalizable reward prediction, including adaptation to five long-horizon tasks, (ii) benefits from pretraining and composing subtask progress estimates, and (iii) improved downstream policy performance.

Explore similar work

CardsList
  1. RoboLongR: Causally Consistent Rewards Teach Robots to Progressively Master Long-Horizon Manipulation

    Oct 24, 2026Zixuan Chen, Lin Cao, Fenggang Zhang +5Long-Horizon Robotic ManipulationRobot Policy Adaptation

  2. RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation

    Jun 20, 2026Pengzhi Yang, Xinyu Wang, Pengyu Jing +7Process Reward ModelsLong-Horizon Robotic Manipulation

  3. ProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation

    May 9, 2026Youhe Feng, Hansen Shi, Haoyang Li +7Robot Task Progress EstimationLong-Horizon Robotic Manipulation