MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains

• URL: http://arxiv.org/abs/2508.18260v1
• Date: Mon, 25 Aug 2025 17:53:22 GMT
• Title: MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains
• Authors: Kaiwen Wei, Rui Shan, Dongsheng Zou, Jianzhong Yang, Bi Zhao, Junnan Zhu, Jiang Zhong,
• Abstract summary: MIRAGE (Multi-chain Inference with Retrieval-Augmented Graph Exploration) is a novel test-time scalable reasoning framework.<n>It performs dynamic multi-chain inference over structured medical knowledge graphs.<n>It consistently outperforms GPT-4o, Tree-of-Thought variants, and other retrieval-augmented baselines in both automatic and human evaluations.
• Score: 19.018680886214035
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large reasoning models (LRMs) have shown significant progress in test-time scaling through chain-of-thought prompting. Current approaches like search-o1 integrate retrieval augmented generation (RAG) into multi-step reasoning processes but rely on a single, linear reasoning chain while incorporating unstructured textual information in a flat, context-agnostic manner. As a result, these approaches can lead to error accumulation throughout the reasoning chain, which significantly limits its effectiveness in medical question-answering (QA) tasks where both accuracy and traceability are critical requirements. To address these challenges, we propose MIRAGE (Multi-chain Inference with Retrieval-Augmented Graph Exploration), a novel test-time scalable reasoning framework that performs dynamic multi-chain inference over structured medical knowledge graphs. Specifically, MIRAGE 1) decomposes complex queries into entity-grounded sub-questions, 2) executes parallel inference chains, 3) retrieves evidence adaptively via neighbor expansion and multi-hop traversal, and 4) integrates answers using cross-chain verification to resolve contradictions. Experiments on three medical QA benchmarks (GenMedGPT-5k, CMCQA, and ExplainCPE) show that MIRAGE consistently outperforms GPT-4o, Tree-of-Thought variants, and other retrieval-augmented baselines in both automatic and human evaluations. Additionally, MIRAGE improves interpretability by generating explicit reasoning chains that trace each factual claim to concrete chains within the knowledge graph, making it well-suited for complex medical reasoning scenarios. The code will be available for further research.

Related papers

• MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains [79.14584837105808]
  We present MC-Search, the first benchmark for agentic MM-RAG with long, step-wise annotated reasoning chains spanning five representative reasoning structures.<n>Beyond answer accuracy, MC-Search introduces new process-level metrics for reasoning quality, stepwise retrieval and planning accuracy.<n>By developing a unified agentic MM-RAG pipeline, we benchmark six leading MLLMs and reveal systematic issues such as over- and under-retrieval and modality-misaligned planning.
  arXiv  Detail & Related papers  (2026-03-01T02:25:57Z)
• HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG [53.30561659838455]
  Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations.<n>Retrieval-Augmented Generation (RAG) frequently overlooks structural interdependencies essential for multi-hop reasoning.<n>Help achieves competitive performance across multiple simple and multi-hop QA benchmarks and up to a 28.8$times$ speedup over leading Graph-based RAG baselines.
  arXiv  Detail & Related papers  (2026-02-24T14:05:29Z)
• CoT-Seg: Rethinking Segmentation with Chain-of-Thought Reasoning and Self-Correction [50.67483317563736]
  This paper aims to explore a system that can think step-by-step, look up information if needed, generate results, self-evaluate its own results, and refine the results.<n>We introduce CoT-Seg, a training-free framework that rethinks reasoning segmentation by combining chain-of-thought reasoning with self-correction.
  arXiv  Detail & Related papers  (2026-01-24T11:41:54Z)
• M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding [66.78251988482222]
  Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by encouraging step-by-step intermediate reasoning.<n>Current benchmarks for medical image understanding generally focus on the final answer while ignoring the reasoning path.<n>M3CoTBench aims to foster the development of transparent, trustworthy, and diagnostically accurate AI systems for healthcare.
  arXiv  Detail & Related papers  (2026-01-13T17:42:27Z)
• Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning [137.33138614095435]
  Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models.<n>Recent efforts have incorporated search-based interactions into RAG, enabling iterative reasoning with real-time retrieval.<n>We propose Bi-RAR, a novel retrieval-augmented reasoning framework that evaluates each intermediate step jointly in both forward and backward directions.
  arXiv  Detail & Related papers  (2025-11-12T08:29:39Z)
• DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA [8.598540768292809]
  Multi-hop reasoning for question answering plays a critical role in retrieval-augmented generation.<n>We propose a novel dual-track KG verification and reasoning framework DTKG.
  arXiv  Detail & Related papers  (2025-10-18T02:19:11Z)
• Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs [69.10441885629787]
  Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge.<n>It falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts.<n>This survey synthesizes both strands under a unified reasoning-retrieval perspective.
  arXiv  Detail & Related papers  (2025-07-13T03:29:41Z)
• Causal Graphs Meet Thoughts: Enhancing Complex Reasoning in Graph-Augmented LLMs [4.701165676405066]
  It is critical not only to retrieve relevant information but also to provide causal reasoning and explainability.<n>This paper proposes a novel pipeline that filters large knowledge graphs to emphasize cause-effect edges.<n> Experiments on medical question-answering tasks show consistent gains, with up to a 10% absolute improvement.
  arXiv  Detail & Related papers  (2025-01-24T19:31:06Z)
• Chain-of-Retrieval Augmented Generation [72.06205327186069]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)
• TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation [30.485127201645437]
  We propose TRACE to enhance the multi-hop reasoning ability of RAG models. TRACE constructs knowledge-grounded reasoning chains, which are a series of logically connected knowledge triples. TRACE achieves an average performance improvement of up to 14.03% compared to using all the retrieved documents.
  arXiv  Detail & Related papers  (2024-06-17T12:23:32Z)
• Answering Questions by Meta-Reasoning over Multiple Chains of Thought [53.55653437903948]
  We introduce Multi-Chain Reasoning (MCR), an approach which prompts large language models to meta-reason over multiple chains of thought. MCR examines different reasoning chains, mixes information between them and selects the most relevant facts in generating an explanation and predicting the answer.
  arXiv  Detail & Related papers  (2023-04-25T17:27:37Z)

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.