# Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons

arXiv: https://arxiv.org/abs/2603.02115 · HTML: https://mlsanity.com/paper/2603.02115/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 125 of its 145 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 30 of 125)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [A Distributional Perspective on Reinforcement Learning](https://mlsanity.com/paper/1707.06887/) (2017)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization](https://mlsanity.com/paper/1603.00448/) (2016)

## Built on by (most cited first, 30 of 60)

- [RLDX-1 Technical Report](https://mlsanity.com/paper/2605.03269/) (2026)
- [Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models](https://mlsanity.com/paper/2603.16065/) (2026)
- [Addressing the Orchestration Gap in Generalist Robots via Physical Agency](https://mlsanity.com/paper/2607.21725/) (2026)
- [ARM: Advantage Reward Modeling for Long-Horizon Manipulation](https://mlsanity.com/paper/2604.03037/) (2026)
- [ProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation](https://mlsanity.com/paper/2605.08774/) (2026)
- [RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance](https://mlsanity.com/paper/2608.09853/) (2026)
- [Improving Robotic Generalist Policies via Flow Reversal Steering](https://mlsanity.com/paper/2606.13675/) (2026)
- [Vesta: A Generalist Embodied Reasoning Model](https://mlsanity.com/paper/2606.20905/) (2026)
- [ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI](https://mlsanity.com/paper/2607.04426/) (2026)
- [Progress Reward Modeling for Robotic Learning: A Comprehensive Survey](https://mlsanity.com/paper/2607.21655/) (2026)
- [RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy](https://mlsanity.com/paper/2607.27782/) (2026)
- [Scaling Automatic Research Agents via World Models](https://mlsanity.com/paper/2608.12564/) (2026)
- [SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning](https://mlsanity.com/paper/2603.28730/) (2026)
- [DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models](https://mlsanity.com/paper/2606.17362/) (2026)
- [VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models](https://mlsanity.com/paper/2606.21386/) (2026)
- [RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation](https://mlsanity.com/paper/2606.22027/) (2026)
- [PRM-as-a-Judge 1.5: A Toolkit for Robot Process Assessment](https://mlsanity.com/paper/2608.14284/) (2026)
- [Rewarding DINO: Predicting Dense Rewards with Vision Foundation Models](https://mlsanity.com/paper/2603.16978/) (2026)
- [SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation](https://mlsanity.com/paper/2606.10305/) (2026)
- [PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space](https://mlsanity.com/paper/2606.17924/) (2026)
- [DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation](https://mlsanity.com/paper/2607.13033/) (2026)
- [SAFECAST: Robust Failure Detection for VLA Policies with Contrast-Set Training and Calibration](https://mlsanity.com/paper/2608.04246/) (2026)
- [ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models](https://mlsanity.com/paper/2608.13438/) (2026)
- [Grounded World Model for Semantically Generalizable Planning](https://mlsanity.com/paper/2604.11751/) (2026)
- [DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies](https://mlsanity.com/paper/2605.11750/) (2026)
- [Reinforcing VLAs in Task-Agnostic World Models](https://mlsanity.com/paper/2605.12334/) (2026)
- [Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations](https://mlsanity.com/paper/2605.22123/) (2026)
- [StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement](https://mlsanity.com/paper/2606.00267/) (2026)
- [Learning Process Rewards via Success Visitation Matching for Efficient RL](https://mlsanity.com/paper/2606.23640/) (2026)
- [Freeform Preference Learning for Robotic Manipulation](https://mlsanity.com/paper/2606.32027/) (2026)

## Abstract (arXiv)

General-purpose robot reward models are typically trained to predict absolute task progress from expert demonstrations, providing only local, frame-level supervision. While effective for expert demonstrations, this paradigm scales poorly to large-scale robotics datasets where failed and suboptimal trajectories are abundant and assigning dense progress labels is ambiguous. We introduce Robometer, a scalable reward modeling framework that combines intra-trajectory progress supervision with inter-trajectory preference supervision. Robometer is trained with a dual objective: a frame-level progress loss that anchors reward magnitude on expert data, and a trajectory-comparison preference loss that imposes global ordering constraints across trajectories of the same task, enabling effective learning from both real and augmented failed trajectories. To support this formulation at scale, we curate RBM-1M, a reward-learning dataset comprising over one million trajectories spanning diverse robot embodiments and tasks, including substantial suboptimal and failure data. Across benchmarks and real-world evaluations, Robometer learns more generalizable reward functions than prior methods and improves robot learning performance across a diverse set of downstream applications. Code, model weights, and videos at https://robometer.github.io/.