TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering
For KGQA researchers, TRACE addresses fragmented reasoning in multi-hop question answering by integrating prior exploration patterns, offering a novel approach to improve reasoning coherence.
TRACE introduces an experiential framework for multi-hop KGQA that uses LLM-driven contextual reasoning and reusable exploration priors to improve coherence. It achieves state-of-the-art results on multiple benchmarks, outperforming existing methods.
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.