用大模型逐步推演动作变化，解决动态推理问题
ProRAC: A Neuro-symbolic Method for Reasoning about Actions with LLM-based Progression
- 将动作与问题分解后逐步执行，生成最终状态
- 在多个基准上表现优异，适应不同任务和模型
- 适合需要逻辑推理的智能系统开发
本文提出ProRAC（基于进展的动作与变化推理），一种神经符号框架，利用大模型解决动作与变化推理（RAC）问题。ProRAC从问题中提取动作和疑问，逐步执行每个动作以推导出最终状态，并根据进展后的状态评估查询，得出答案。我们在多个RAC基准上评估了ProRAC，结果表明该方法在不同基准、领域、大模型底座及任务类型下均表现出色。
原文摘要 · Abstract (English)
In this paper, we propose ProRAC (Progression-based Reasoning about Actions and Change), a neuro-symbolic framework that leverages LLMs to tackle RAC problems. ProRAC extracts fundamental RAC elements including actions and questions from the problem, progressively executes each action to derive the final state, and then evaluates the query against the progressed state to arrive at an answer. We evaluate ProRAC on several RAC benchmarks, and the results demonstrate that our approach achieves strong performance across different benchmarks, domains, LLM backbones, and types of RAC tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。