# Rethinking Reward Models for Multi-Domain Test-Time Scaling

arXiv: https://arxiv.org/abs/2510.00492 · HTML: https://mlsanity.com/paper/2510.00492/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 65 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [A Survey on Data Selection for Language Models](https://mlsanity.com/paper/2402.16827/) (2024)
- [Nemotron-4 340B Technical Report](https://mlsanity.com/paper/2406.11704/) (2024)
- [Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture](https://mlsanity.com/paper/2306.16092/) (2023)
- [Process Reward Models That Think](https://mlsanity.com/paper/2504.16828/) (2025)
- [GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning](https://mlsanity.com/paper/2504.00891/) (2025)
- [Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination](https://mlsanity.com/paper/2507.10532/) (2025)
- [Self-Taught Evaluators](https://mlsanity.com/paper/2408.02666/) (2024)
- [GRACE: Discriminator-Guided Chain-of-Thought Reasoning](https://mlsanity.com/paper/2305.14934/) (2023)

## Built on by (most cited first, 10 of 10)

- [A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models](https://mlsanity.com/paper/2510.08049/) (2025)
- [Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding](https://mlsanity.com/paper/2606.00564/) (2026)
- [PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning](https://mlsanity.com/paper/2605.13467/) (2026)
- [Judging What We Cannot Solve: A Consequence-Based Approach for Oracle-Free Evaluation of Research-Level Math](https://mlsanity.com/paper/2602.06291/) (2026)
- [Test-Time Scaling for Small VLMs on Multilingual Visual MCQ](https://mlsanity.com/paper/2607.09438/) (2026)
- [Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents](https://mlsanity.com/paper/2609.39982/) (2026)
- [From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models](https://mlsanity.com/paper/2511.10899/) (2025)
- [MAPLE: Elevating Medical Reasoning from Statistical Consensus to Process-Led Alignment](https://mlsanity.com/paper/2603.08987/) (2026)
- [Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA](https://mlsanity.com/paper/2609.16660/) (2026)
- [RGDT-Bench: Benchmarking LLM Reasoning for Rule-Governed Decisions and Their Justifications](https://mlsanity.com/paper/2609.34455/) (2026)

## Abstract (arXiv)

The reliability of large language models (LLMs) during test-time scaling is often assessed with external verifiers or reward models that distinguish correct reasoning from flawed logic. Prior work has studied both outcome reward models (ORMs), which assess only the final answer, and process reward models (PRMs), which score intermediate reasoning steps. Although PRMs are often viewed as advantageous due to their finer-grained supervision, much of the supporting evidence comes from math-adjacent settings, and their relative benefits across broader domains remain unclear. We present the first unified evaluation of four reward model variants, discriminative ORM and PRM (dORM, dPRM) and generative ORM and PRM (gORM, gPRM), across 14 diverse domains. Contrary to conventional wisdom, we find that (i) dORM performs on par with dPRM, (ii) gPRM is not competitive, and (iii) overall, gORM is the most robust, yielding significant and consistent gains across every tested domain. We attribute the worse performance of gPRM to the stepwise scoring process, which inherits label noise from LLM-based automatic labeling, leading to difficulties in evaluating long reasoning trajectories, including those involving self-correcting reasoning. Both our theoretical analysis and empirical observations indicate that stepwise aggregation compounds errors as reasoning length increases. These findings challenge the common assumption that fine-grained supervision is always better and support generative outcome verification for multi-domain deployment. Our hrefhttps://github.com/db-Lee/Multi-RMunderlinecode is publicly available to facilitate future research in multi-domain settings.