Critic-Guided Heterogeneous Multi-Agent Reasoning for Reliable Mathematical Problem Solving

• URL: http://arxiv.org/abs/2606.05704v1
• Date: Thu, 04 Jun 2026 04:52:35 GMT
• Title: Critic-Guided Heterogeneous Multi-Agent Reasoning for Reliable Mathematical Problem Solving
• Abstract summary: This study introduces a critic-based heterogeneous multi-agent approach to improve the dependability of mathematical reasoning.<n>Experiments on the GSM8K benchmark show that the proposed method achieves up to 13% accuracy improvement over single-shot and non-critic models.
• Score: 0.10768487997600945
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent Large Language Models (LLMs) have shown impressive reasoning abilities; but they are still susceptible to hallucinations, intermediate reasoning mistakes, and unreliable reasoning results in complex mathematical reasoning problems. In this study, we introduce a critic-based heterogeneous multi-agent approach to improve the dependability of mathematical reasoning. This framework incorporates several LLM agents of different specialties and employs a critic-driven adaptive learning system to assess and guide the reasoning process based on intermediate feedback. The system adopts a generator-validator framework, with the validator not only determining correctness but also offering critiques to guide regeneration of solutions. This allows for adaptive error correction and prevents error cascading. Our experiments on the GSM8K benchmark show that the proposed method achieves up to 13% accuracy improvement over single-shot and non-critic models. Additionally, findings suggest that heterogeneity and critique reduce the need for large models, allowing smaller models to perform on par. Ablation studies reveal the main performance gains are due to the critic-based feedback loop and not model size. In summary, the proposed approach showcases the benefits of combining heterogeneous multi-agent collaboration and critique to obtain reliable and interpretable reasoning systems.

Related papers

• Decoding the Critique Mechanism in Large Reasoning Models [50.821607345799386]
  Large Reasoning Models (LRMs) exhibit backtracking and self-verification mechanisms that enable them to revise intermediate steps and reach correct solutions.<n>We investigate how current LRMs recover from errors by inserting arithmetic mistakes in their intermediate reasoning steps.<n>We find that despite the error propagating through the chain-of-thought, the model still reaches the correct final answer.
  arXiv  Detail & Related papers  (2026-03-17T10:03:30Z)
• MSA-Thinker: Discrimination-Calibration Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis [5.1150258716324055]
  Multimodal sentiment analysis aims to understand human emotions by integrating textual, auditory, and visual modalities.<n>Existing methods incorporating Chain-of-Thought (CoT) reasoning are hindered by high annotation costs.<n>We propose a novel training framework that integrates structured Discrimination-Calibration (DC) reasoning with Hint-based Reinforcement Learning.
  arXiv  Detail & Related papers  (2026-03-10T12:48:41Z)
• CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling [61.75914342638658]
  CDRRM (Contrast-Driven Reward Model) is a framework for high-quality rubric generation and guided preference judgment.<n>This work offers a scalable, interpretable, and data-efficient path for reward modeling.
  arXiv  Detail & Related papers  (2026-03-09T07:15:23Z)
• Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models [72.4149653187766]
  We propose a Reasoner-Verifier framework named Adrialversa Reasoning RAG (ARR)<n>The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage.<n> Experiments on multiple benchmarks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2026-01-08T06:57:03Z)
• Counterfactual Self-Questioning for Stable Policy Optimization in Language Models [0.0]
  We propose Counterfactual Self-Questioning, a framework in which a single language model generates and evaluates counterfactual critiques of its own reasoning.<n> Experiments on multiple mathematical reasoning benchmarks show that counterfactual self-questioning improves accuracy and training stability, particularly for smaller models.
  arXiv  Detail & Related papers  (2025-12-31T09:10:37Z)
• Rectify Evaluation Preference: Improving LLMs' Critique on Math Reasoning via Perplexity-aware Reinforcement Learning [34.43632129774481]
  In this paper, we quantify and investigate the potential reason -- imbalanced evaluation preference.<n>Motivated by the analysis of the reason, a novel perplexity-aware reinforcement learning algorithm is proposed to rectify the evaluation preference.
  arXiv  Detail & Related papers  (2025-11-13T13:37:45Z)
• Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers [63.99316853136304]
  Mirror-Critique is a framework that trains a verifier with informative critiques.<n>We deploy a small instruction-tuned model to synthesize high-quality critique data.<n>The resulting Mirror-Verifier is deployed to evaluate candidate solutions by generating multiple critiques per solution.
  arXiv  Detail & Related papers  (2025-09-27T06:50:24Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoning [3.721438719967748]
  Table-Critic is a novel multi-agent framework that facilitates collaborative criticism and iterative refinement of the reasoning process.<n>Our framework consists of four specialized agents: a Judge for error identification, a Critic for comprehensive critiques, a Refiner for process improvement, and a Curator for pattern distillation.<n>Extensive experiments have demonstrated that Table-Critic achieves superior accuracy and error correction rates while maintaining computational efficiency and lower solution degradation rate.
  arXiv  Detail & Related papers  (2025-02-17T13:42:12Z)
• Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning [53.25336975467293]
  We present the first theoretical error decomposition analysis of methods such as perplexity and self-consistency.<n>Our analysis reveals a fundamental trade-off: perplexity methods suffer from substantial model error due to the absence of a proper consistency function.<n>We propose Reasoning-Pruning Perplexity Consistency (RPC), which integrates perplexity with self-consistency, and Reasoning Pruning, which eliminates low-probability reasoning paths.
  arXiv  Detail & Related papers  (2025-02-01T18:09:49Z)
• Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision [120.40788744292739]
  We propose a two-player paradigm that separates the roles of reasoning and critique models. We first propose AutoMathCritique, an automated and scalable framework for collecting critique data. We demonstrate that the critique models consistently improve the actor's performance on difficult queries at test-time.
  arXiv  Detail & Related papers  (2024-11-25T17:11:54Z)

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.