# EQA-RM: A Generative Embodied Reward Model with Test-time Scaling

arXiv: https://arxiv.org/abs/2506.10389 · HTML: https://mlsanity.com/paper/2506.10389/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 23 of 23)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [Scaling Relationship on Learning Mathematical Reasoning with Large Language Models](https://mlsanity.com/paper/2308.01825/) (2023)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025)
- [Generative Reward Models](https://mlsanity.com/paper/2410.12832/) (2024)
- [A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce](https://mlsanity.com/paper/2504.11343/) (2025)
- [VisualPRM: An Effective Process Reward Model for Multimodal Reasoning](https://mlsanity.com/paper/2503.10291/) (2025)
- [Rule Based Rewards for Language Model Safety](https://mlsanity.com/paper/2411.01111/) (2024)
- [GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning](https://mlsanity.com/paper/2504.00891/) (2025)
- [Self-Generated Critiques Boost Reward Modeling for Language Models](https://mlsanity.com/paper/2411.16646/) (2024)
- [Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning](https://mlsanity.com/paper/2505.07527/) (2025)
- [Reward Models Identify Consistency, Not Causality](https://mlsanity.com/paper/2502.14619/) (2025)

## Built on by (most cited first, 2 of 2)

- [Can GRPO Help LLMs Transcend Their Pretraining Origin?](https://mlsanity.com/paper/2510.15990/) (2025)
- [Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning](https://mlsanity.com/paper/2606.08231/) (2026)

## Abstract (arXiv)

Reward Models (RMs), vital for large model alignment, are underexplored for complex embodied tasks like Embodied Question Answering (EQA) where nuanced evaluation of agents' spatial, temporal, and logical understanding is critical yet not considered by generic approaches. We introduce EQA-RM, a novel generative multimodal reward model specifically architected for EQA, trained via our innovative Contrastive Group Relative Policy Optimization (C-GRPO) strategy to learn fine-grained behavioral distinctions. The generative nature of EQA-RM provides interpretable, structured reward feedback (beyond simple scalars), uniquely enabling test-time scaling to dynamically adjust evaluation granularity, from concise scores to detailed critiques of reasoning and grounding, at inference without retraining. Concurrently, we introduce EQARewardBench, a new benchmark built on OpenEQA for standardized EQA reward model assessment. Demonstrating high sample efficiency, EQA-RM (fine-tuning Qwen2-VL-2B-Instruct) achieves 61.9% accuracy on EQA-RM-Bench with only 700 samples, outperforming strong proprietary baselines, including Gemini-2.5-Flash, GPT-4o, Claude-3.5-Haiku, and open-sourced state-of-the-art models such as RoVRM and VisualPRM. The code and dataset can be found here https://github.com/UNITES-Lab/EQA-RM.