THOR: A Theta-Gamma Hierarchical Oscillatory Reasoning Framework for Multi-hop QA

• URL: http://arxiv.org/abs/2607.20459v1
• Date: Fri, 15 May 2026 03:01:22 GMT
• Title: THOR: A Theta-Gamma Hierarchical Oscillatory Reasoning Framework for Multi-hop QA
• Abstract summary: Multi-hop question answering requires retrieving and integrating evidence from multiple contexts.<n> THOR is inspired by Theta-Gamma hierarchical oscillation which decouples global planning from local retrieval.<n> THOR improves answer accuracy and robustness while mitigating limitations, showcasing its generalization across different backbones.
• Score: 1.2768798535259775
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-hop question answering requires retrieving and integrating evidence from multiple contexts. Despite the rapid progress of current research, multi-hop reasoning remains constrained by two persistent limitations: attention decay, where the model's focus on main question degrades as the reasoning chain grows, and error accumulation, where mistakes propagate across hops and compounds into final failure. Inspired by Theta-Gamma hierarchical oscillation which decouples global planning from local retrieval, enabling efficient attention transfer between hops and a verification and repair mechanism that interrupts the accumulation of errors in the wrong paths, we present THOR, a brain-inspired Theta-Gamma hierarchical oscillatory reasoning framework. Extensive comparative experiments and specific validation experiments on multi-hop QA benchmarks demonstrate that THOR improves answer accuracy and robustness while mitigating limitations, showcasing its generalization across different backbones.

Related papers

• SABET-QA: Temporal Knowledge Graph Question Answering [0.0]
  We propose SABET-QA, a framework that iteratively refines reasoning states across multiple hops.<n> Experiments on CronQuestions, Complex-CronQuestions, MultiTQ, and TimeQuestions demonstrate consistent improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-08-20T14:16:35Z)
• D$^2$F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation [44.30305229446082]
  Large language models (LLMs) often generate inaccurate answers due to their reliance on static internal knowledge.<n>Retrieval-augmented generation (RAG) addresses this limitation by integrating external knowledge and excelling at single-hop queries.<n>Existing methods, such as graph structured RAG or question decomposition, often lack dynamic decomposition and effective filtering.<n>We propose Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation (D2F-ReAG)
  arXiv  Detail & Related papers  (2026-08-05T04:41:36Z)
• Compositional Multi-hop Factual Error Correction via Decomposition-and-Injection [60.34509125517578]
  We present CECoR (Compositional Error Correction via Reasoning-aware Synthesis), a reasoning-aware framework for compositional error correction.<n> CECoR decomposes multi-hop claims into interpretable reasoning steps and injects controlled perturbations to synthesize high-quality training pairs.<n>A two-stage learning strategy combining supervised fine-tuning and reinforcement learning improves factual accuracy and robustness.
  arXiv  Detail & Related papers  (2026-05-04T07:08:39Z)
• CRAFT: Calibrated Reasoning with Answer-Faithful Traces via Reinforcement Learning for Multi-Hop Question Answering [19.391824811629125]
  Retrieval-augmented generation (RAG) is widely used to ground Large Language Models (LLMs) for multi-hop question answering.<n> Reasoning in multi-hop QA is inherently complex due to multi-hop composition and is further destabilized by noisy retrieval.<n>We propose CRAFT, a reinforcement learning framework that trains models to perform faithful reasoning during response generation.
  arXiv  Detail & Related papers  (2026-02-01T17:33:39Z)
• Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models [66.36240676392502]
  Chain-of-thought (CoT) reasoning has become the standard paradigm for enabling Large Language Models (LLMs) to solve complex problems.<n>Recent studies reveal a sharp performance drop in reasoning hop generalization scenarios.<n>We propose test-time correction of reasoning, a lightweight intervention method that dynamically identifies and deactivates ep heads in the reasoning process.
  arXiv  Detail & Related papers  (2026-01-29T03:24:32Z)
• Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering [14.456873356080186]
  Reasoning Tree Guided RAG (RT-RAG) is a novel hierarchical framework for complex multi-hop QA.<n>RT-RAG systematically decomposes multi-hop questions into explicit reasoning trees, minimizing inaccurate decomposition.
  arXiv  Detail & Related papers  (2026-01-16T13:02:25Z)
• Reinforcement Learning Enhanced Multi-hop Reasoning for Temporal Knowledge Question Answering [16.044892597109563]
  Temporal knowledge graph question answering (TKGQA) involves multi-hop reasoning over temporally constrained entity relationships.<n>We propose the multi-hop reasoning enhanced (MRE) framework, which enhances both forward and backward reasoning.<n>We show that the proposed MRE-based model consistently surpasses state-of-the-art (SOTA) approaches in handling complex multi-hop queries.
  arXiv  Detail & Related papers  (2026-01-03T14:27:01Z)
• Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics [89.1999907891494]
  We present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox.<n>Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures.<n>We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies.
  arXiv  Detail & Related papers  (2025-10-01T07:59:03Z)
• Credible Plan-Driven RAG Method for Multi-Hop Question Answering [2.5772544412212985]
  We propose PAR-RAG (Plan-then-Act-and-Review RAG), a novel framework inspired by the PDCA (Plan-Do-Check-Act) cycle.<n>Par-RAG selects exemplars matched by the semantic complexity of the current question to guide complexity-aware top-down planning.<n>A dual-verification mechanism evaluates and corrects intermediate errors, ensuring that the reasoning process remains factually grounded.
  arXiv  Detail & Related papers  (2025-04-23T15:03:17Z)
• GRITHopper: Decomposition-Free Multi-Hop Dense Retrieval [52.47514434103737]
  We introduce GRITHopper-7B, a novel multi-hop dense retrieval model that achieves state-of-the-art performance.<n> GRITHopper combines generative and representational instruction tuning by integrating causal language modeling with dense retrieval training.<n>We find that incorporating additional context after the retrieval process, referred to as post-retrieval language modeling, enhances dense retrieval performance.
  arXiv  Detail & Related papers  (2025-03-10T16:42:48Z)
• Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering [71.49131159045811]
  Multi-hop reasoning requires aggregating multiple documents to answer a complex question. Existing methods usually decompose the multi-hop question into simpler single-hop questions. We propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation.
  arXiv  Detail & Related papers  (2022-08-22T13:24:25Z)
• Modeling Multi-hop Question Answering as Single Sequence Prediction [88.72621430714985]
  We propose a simple generative approach (PathFid) that extends the task beyond just answer generation. PathFid explicitly models the reasoning process to resolve the answer for multi-hop questions. Our experiments demonstrate that PathFid leads to strong performance gains on two multi-hop QA datasets.
  arXiv  Detail & Related papers  (2022-05-18T21:57:59Z)

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.