Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models

• URL: http://arxiv.org/abs/2603.01571v1
• Date: Mon, 02 Mar 2026 07:54:29 GMT
• Title: Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models
• Authors: Qiyuan Zhang, Yufei Wang, Tianhe Wu, Can Xu, Qingfeng Sun, Kai Zheng, Xue Liu, Chen Ma,
• Abstract summary: We introduce Mix-GRM, a framework that reconfigures raw rationales into structured B-CoT and D-CoT through a modular synthesis pipeline.<n>Experiments demonstrate that Mix-GRM establishes a new state-of-the-art across five benchmarks, surpassing leading open-source RMs by an average of 8.2%.
• Score: 39.290072292743226
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in Generative Reward Models (GRMs) have demonstrated that scaling the length of Chain-of-Thought (CoT) reasoning considerably enhances the reliability of evaluation. However, current works predominantly rely on unstructured length scaling, ignoring the divergent efficacy of different reasoning mechanisms: Breadth-CoT (B-CoT, i.e., multi-dimensional principle coverage) and Depth-CoT (D-CoT, i.e., substantive judgment soundness). To address this, we introduce Mix-GRM, a framework that reconfigures raw rationales into structured B-CoT and D-CoT through a modular synthesis pipeline, subsequently employing Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR) to internalize and optimize these mechanisms. Comprehensive experiments demonstrate that Mix-GRM establishes a new state-of-the-art across five benchmarks, surpassing leading open-source RMs by an average of 8.2\%. Our results reveal a clear divergence in reasoning: B-CoT benefits subjective preference tasks, whereas D-CoT excels in objective correctness tasks. Consequently, misaligning the reasoning mechanism with the task directly degrades performance. Furthermore, we demonstrate that RLVR acts as a switching amplifier, inducing an emergent polarization where the model spontaneously allocates its reasoning style to match task demands. The synthesized data and models are released at \href{https://huggingface.co/collections/DonJoey/mix-grm}{Hugging Face}, and the code is released at \href{https://github.com/Don-Joey/Mix-GRM}{Github}.

Related papers

• Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling [49.41422138354821]
  We propose a principled reward modeling framework that integrates non-negative factor analysis into the Bradley-Terry preference model.<n>BNRM represents rewards through a sparse, non-negative latent factor generative process.<n>We show that BNRM substantially mitigates reward over-optimization, improves robustness under distribution shifts, and yields more interpretable reward decompositions than strong baselines.
  arXiv  Detail & Related papers  (2026-02-11T08:14:11Z)
• Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervision [11.159231524113764]
  Reinforcement Learning (RL) has emerged as a pivotal mechanism for enhancing the complex reasoning capabilities of Multimodal Large Language Models (MLLMs)<n>In this paper, we propose the textbfGuided Verifier framework to address these structural limitations.<n>We develop a specialized data synthesis pipeline targeting multimodal hallucinations, constructing textbfCoRe dataset of process-level negatives and textbfCorrect-guide textbfReasoning trajectories to train the guided verifier.
  arXiv  Detail & Related papers  (2026-02-04T07:38:42Z)
• Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations [55.047454145941366]
  Streaming Merging is an innovative model updating paradigm that conceptualizes merging as an iterative optimization process.<n> ARM is a strategy designed to approximate gradient descent dynamics.<n> ARM requires only early SFT checkpoints and, through iterative merging, surpasses the fully converged SFT model.
  arXiv  Detail & Related papers  (2026-02-03T08:15:57Z)
• Mixture-of-Models: Unifying Heterogeneous Agents via N-Way Self-Evaluating Deliberation [0.0]
  This paper introduces the N-Way Self-Evaluating Deliberation (NSED) protocol, a Mixture-of-Models (MoM) architecture that constructs emergent composite models from a plurality of distinct expert agents.<n>Unlike traditional Mixture-of-Experts (MoE) which rely on static gating networks, NSED employs a Dynamic Expertise Broker that treats model selection as a variation of the Knapsack Problem.
  arXiv  Detail & Related papers  (2026-01-23T16:11:54Z)
• CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning [93.05917922306196]
  Composed Image Retrieval (CIR) aims to find a target image from a reference image and a modification text.<n>CIR-CoT is the first end-to-end retrieval-oriented MLLM designed to integrate explicit Chain-of-Thought (CoT) reasoning.
  arXiv  Detail & Related papers  (2025-10-09T09:41:45Z)
• ACD-CLIP: Decoupling Representation and Dynamic Fusion for Zero-Shot Anomaly Detection [21.26826497960086]
  Pre-trained Vision-Language Models (VLMs) struggle with Zero-Shot Anomaly Detection (ZSAD)<n>We propose a parameter-efficient Convolutional Low-Rank Adaptation (Conv-LoRA) adapter to inject local inductive biases for fine-grained representation.<n>We also introduce a Dynamic Fusion Gateway (DFG) that leverages visual context to adaptively modulate text prompts.
  arXiv  Detail & Related papers  (2025-08-11T10:03:45Z)
• Latent Diffusion Model Based Denoising Receiver for 6G Semantic Communication: From Stochastic Differential Theory to Application [11.385703484113552]
  We propose a novel semantic communication framework empowered by generative artificial intelligence (GAI)<n>A latent diffusion model (LDM)-based semantic communication framework is proposed that combines a variational autoencoder for semantic features extraction.<n>The proposed system is a training-free framework that supports zero-shot generalization, and achieves superior performance under low-SNR and out-of-distribution conditions.
  arXiv  Detail & Related papers  (2025-06-06T03:20:32Z)
• Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models [50.4652276723694]
  Think-RM generates flexible, self-guided reasoning traces that support advanced capabilities.<n>Think-RM achieves state-of-the-art results on RM-Bench, outperforming both BT RM and vertically scaled GenRM by 8%.
  arXiv  Detail & Related papers  (2025-05-22T05:56:11Z)
• Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models [46.75272311751018]
  We propose a novel reward model approach called the Hierarchical Reward Model.<n>It evaluates both individual and consecutive reasoning steps at both fine-grained and coarse-grained levels.<n>It excels at assessing multi-step reasoning coherence, especially when flawed steps are later corrected through self-reflection.
  arXiv  Detail & Related papers  (2025-03-16T15:18:40Z)
• Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models [39.22557129190619]
  Distillation--post-training on LRMs-generated data--is a straightforward yet effective method to enhance the reasoning abilities of smaller models.<n>To alleviate this bottleneck, we propose constructing tree-based CoT data from scratch via Monte Carlo Tree Search.<n>We then exploit a set of CoT-aware approaches, including Thoughts Length Balance, Fine-grained DPO, and Joint Post-training Objective, to enhance SFT and RL on the constructed data.
  arXiv  Detail & Related papers  (2025-03-03T12:17:36Z)
• Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs [63.36637269634553]
  We introduce a novel approach where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step.<n>We show that fine-tuning on DCoT improves performance over the CoT baseline across model families and scales.<n>Our work is also significant because both quantitative analyses and manual evaluations reveal the observed gains stem from the models' ability to refine an initial reasoning chain.
  arXiv  Detail & Related papers  (2024-07-03T15:01:18Z)

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.