A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning

• URL: http://arxiv.org/abs/2509.22044v1
• Date: Fri, 26 Sep 2025 08:27:03 GMT
• Title: A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning
• Authors: Ziqi Wang, Boye Niu, Zhongli Li, Linghui Meng, Jing Liu, Zhi Zheng, Tong Xu, Hua Wu, Haifeng Wang, Enhong Chen,
• Abstract summary: Asymmetric Two-Stage Reasoning framework designed to bridge gap between a model's potential and its actual performance.<n>A2R-Efficient is a "small-to-big" variant that combines a Qwen3-4B explorer with a Qwen3-8B synthesizer.<n>Results show A2R is not only a performance-boosting framework but also an efficient and practical solution for real-world applications.
• Score: 57.727084580884075
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent Large Reasoning Models have achieved significant improvements in complex task-solving capabilities by allocating more computation at the inference stage with a "thinking longer" paradigm. Even as the foundational reasoning capabilities of models advance rapidly, the persistent gap between a model's performance in a single attempt and its latent potential, often revealed only across multiple solution paths, starkly highlights the disparity between its realized and inherent capabilities. To address this, we present A2R, an Asymmetric Two-Stage Reasoning framework designed to explicitly bridge the gap between a model's potential and its actual performance. In this framework, an "explorer" model first generates potential solutions in parallel through repeated sampling. Subsequently,a "synthesizer" model integrates these references for a more refined, second stage of reasoning. This two-stage process allows computation to be scaled orthogonally to existing sequential methods. Our work makes two key innovations: First, we present A2R as a plug-and-play parallel reasoning framework that explicitly enhances a model's capabilities on complex questions. For example, using our framework, the Qwen3-8B-distill model achieves a 75% performance improvement compared to its self-consistency baseline. Second, through a systematic analysis of the explorer and synthesizer roles, we identify an effective asymmetric scaling paradigm. This insight leads to A2R-Efficient, a "small-to-big" variant that combines a Qwen3-4B explorer with a Qwen3-8B synthesizer. This configuration surpasses the average performance of a monolithic Qwen3-32B model at a nearly 30% lower cost. Collectively, these results show that A2R is not only a performance-boosting framework but also an efficient and practical solution for real-world applications.

Related papers

• Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey [92.71325249013535]
  Deliberative tree search is a cornerstone of Large Language Model (LLM) research.<n>This paper introduces a unified framework that deconstructs search algorithms into three core components.
  arXiv  Detail & Related papers  (2025-10-11T03:29:18Z)
• THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning [25.605096023894834]
  Large Language Models (LLMs) have made remarkable progress in mathematical reasoning.<n>Despite recent advances, existing methods struggle with three key challenges.<n>We propose THOR (Tool-Integrated Hierarchical Optimization via RL) to overcome these limitations.<n>Our approach demonstrates strong generalization across diverse models, performing effectively in both reasoning and non-reasoning models.
  arXiv  Detail & Related papers  (2025-09-17T07:16:12Z)
• Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models [57.49136894315871]
  New paradigm of test-time scaling has yielded remarkable breakthroughs in reasoning models and generative vision models.<n>We propose one solution to the problem of integrating test-time scaling knowledge into a model during post-training.<n>We replace reward guided test-time noise optimization in diffusion models with a Noise Hypernetwork that modulates initial input noise.
  arXiv  Detail & Related papers  (2025-08-13T17:33:37Z)
• SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution [55.14432034345353]
  We study key design principles for latter cascaded video super-resolution models, which are underexplored currently.<n>First, we propose two strategies to generate training pairs that better mimic the output characteristics of the base model, ensuring alignment between the VSR model and its upstream generator.<n>Second, we provide critical insights into VSR model behavior through systematic analysis of (1) timestep sampling strategies, (2) noise augmentation effects on low-resolution (LR) inputs.
  arXiv  Detail & Related papers  (2025-06-24T17:57:26Z)
• Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition [95.54406667705999]
  Pangu Embedded is an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs)<n>It addresses the significant computational costs and inference latency challenges prevalent in existing reasoning-optimized LLMs.<n>It delivers rapid responses and state-of-the-art reasoning quality within a single, unified model architecture.
  arXiv  Detail & Related papers  (2025-05-28T14:03:02Z)
• SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models [21.933379266533098]
  Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost.<n>Existing serving strategies often employ fixed model scales or static two-stage speculative decoding.<n>This paper introduces systemname, a novel framework that reimagines LLM inference as an adaptive routing problem.
  arXiv  Detail & Related papers  (2025-05-12T15:46:28Z)
• Reinforced Model Merging [53.84354455400038]
  We present an innovative framework termed Reinforced Model Merging (RMM), which encompasses an environment and agent tailored for merging tasks.<n>By utilizing data subsets during the evaluation process, we addressed the bottleneck in the reward feedback phase, thereby accelerating RMM by up to 100 times.
  arXiv  Detail & Related papers  (2025-03-27T08:52:41Z)
• Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging [17.038807261969033]
  Long-to-Short (L2S) reasoning aims to balance reasoning depth with practical efficiency.<n>Model merging offers a cost-effective and robust alternative by integrating the quick-thinking capabilities of System 1 models with the methodical reasoning of System 2 models.<n>Our experiments reveal that model merging can reduce average response length by up to 55% while preserving or even improving baseline performance.
  arXiv  Detail & Related papers  (2025-03-26T15:34:37Z)
• A Lightweight Feature Fusion Architecture For Resource-Constrained Crowd Counting [3.5066463427087777]
  We introduce two lightweight models to enhance the versatility of crowd-counting models. These models maintain the same downstream architecture while incorporating two distinct backbones: MobileNet and MobileViT. We leverage Adjacent Feature Fusion to extract diverse scale features from a Pre-Trained Model (PTM) and subsequently combine these features seamlessly.
  arXiv  Detail & Related papers  (2024-01-11T15:13:31Z)
• Efficient Person Search: An Anchor-Free Approach [86.45858994806471]
  Person search aims to simultaneously localize and identify a query person from realistic, uncropped images. To achieve this goal, state-of-the-art models typically add a re-id branch upon two-stage detectors like Faster R-CNN. In this work, we present an anchor-free approach to efficiently tackling this challenging task, by introducing the following dedicated designs.
  arXiv  Detail & Related papers  (2021-09-01T07:01:33Z)

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.