RACER：面向知识图谱可解释推理的强化智能体协作框架
RACER: Reinforced Agent Collaboration for Explainable Reasoning on Knowledge Graphs
浏览论文内容
中文总结 AI 辅助
RACER是面向知识图谱可解释推理的强化智能体协作框架，通过多智能体协作等技术解决LLM的幻觉与复杂推理难题，在两个数据集上平均提升5%性能。
中文摘要 AI 辅助
大型语言模型（LLMs）常存在幻觉问题，且难以完成需要多跳领域知识的复杂推理任务。知识图谱（KGs）虽能提供结构化、可验证的信息源，但当前KG增强型LLM范式通常依赖单智能体路径提取和固定提示，缺乏适应性且面临巨大的搜索空间。为解决这些挑战，本文提出RACER——面向知识图谱可解释推理的强化智能体协作框架。RACER采用语义感知动作剪枝和教师引导的强化学习机制，可从大规模KG中高效提取高质量推理路径。此外，为缓解单路径生成的缺陷，本文引入跨任务累积共享记忆图，并搭配注意力驱动的多路径知识精修模块。最后，RACER通过四角色多智能体协作系统（GraphAgent、TemplateAgent、AnswerAgent和CriticAgent）协调各组件，动态优化提示并评估答案。在CommonsenseQA和OpenBookQA数据集上的大量实验表明，RACER显著优于当前最优的KG增强型LLM基线，平均提升5%，具备强大且高度可解释的推理能力。
英文摘要
Large Language Models (LLMs) often suffer from hallucination and struggle with complex reasoning tasks requiring multi-hop domain knowledge. While integrating Knowledge Graphs (KGs) provides a structured and verifiable information source, current KG-enhanced LLM paradigms usually rely on single-agent path extraction and fixed prompting, lacking adaptability and facing huge search spaces. To address these challenges, we propose RACER, a Reinforced Agent Collaboration framework for Explainable Reasoning on knowledge graphs. RACER employs a semantic-aware action pruning and teacher-guided reinforcement learning mechanism to efficiently extract high-quality reasoning pathways from large-scale KGs. Furthermore, to mitigate single-path generation pitfalls, we introduce a cross-task accumulated shared memory graph paired with an attention-driven multi-path knowledge refinement module. Finally, RACER orchestrates these components through a four-role multi-agent collaboration system (GraphAgent, TemplateAgent, AnswerAgent, and CriticAgent) to dynamically refine prompts and evaluate answers. Extensive experiments on CommonsenseQA and OpenBookQA datasets demonstrate that RACER significantly outperforms state-of-the-art KG-enhanced LLM baselines with an average improvement of 5\%, offering robust and highly interpretable reasoning capabilities.
发表机构
- State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）
- Chinaunicom Software Nanjing Branch（中国联通软件南京分公司）
机构由 AI 辅助整理，请以论文原文为准。
