TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering

2026-04-13

AI Summary

This work addresses the challenges in multi-hop knowledge graph question answering (KGQA), where fragmented reasoning processes and the inability to reuse past exploration experiences often lead to incoherent inference and redundant search. To overcome these limitations, the authors propose TRACE, a novel framework that introduces, for the first time, a trajectory-aware dual feedback re-ranking mechanism. TRACE dynamically converts reasoning paths into semantically coherent natural language narratives and abstracts historical trajectories into transferable exploration priors, thereby enabling experience-driven, coherent reasoning. By integrating large language models, path-to-narrative generation, and prior learning, the method significantly outperforms state-of-the-art approaches across multiple KGQA benchmarks, demonstrating clear advantages in both reasoning coherence and answer accuracy.

Technology Category

• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Knowledge Representation and Reasoning: Knowledge Acquisition
• Natural Language Processing: Question Answering

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Multi-hop Knowledge Graph Question Answering (KGQA) requires coherent reasoning across relational paths, yet existing methods often treat each reasoning step independently and fail to effectively leverage experience from prior explorations, leading to fragmented reasoning and redundant exploration. To address these challenges, we propose Trajectoryaware Reasoning with Adaptive Context and Exploration priors (TRACE), an experiential framework that unifies LLM-driven contextual reasoning with exploration prior integration to enhance the coherence and robustness of multihop KGQA. Specifically, TRACE dynamically translates evolving reasoning paths into natural language narratives to maintain semantic continuity, while abstracting prior exploration trajectories into reusable experiential priors that capture recurring exploration patterns. A dualfeedback re-ranking mechanism further integrates contextual narratives with exploration priors to guide relation selection during reasoning. Extensive experiments on multiple KGQA benchmarks demonstrate that TRACE consistently outperforms state-of-the-art baselines.

Problem

• multi-hop KGQA
• coherent reasoning
• knowledge graph question answering
• reasoning paths
• exploration redundancy

Innovation

• multi-hop KGQA
• experiential reasoning
• exploration priors
• contextual narrative
• dual-feedback re-ranking