Reasoning

Memory, Reasoning, and Planning of Language Agents

Language Agents have emerged as one of the most exciting research directions in AI over the past two years. This article explores three core components: long-term memory via HippoRAG, reasoning capabilities with Grokked Transformers, and world modeling through WebDreamer. Why Agents Again? Russell & Norvig in “Artificial Intelligence: A Modern Approach” define an agent as “anything that can perceive its environment through sensors and act upon that environment through actions.”（@ArtificialIntelligenceModern） ...

大语言模型的自我提升与推理能力进化(Jason Weston, Meta)

本文内容来自 Jason Weston (Meta) 在 UC Berkeley Advanced Large Language Model Agents 课程中的分享，探讨了大语言模型的推理能力提升。以下为讲座内容： AI 能力正在快速发展，如 O1、R1 等模型在推理基准测试中取得的突破性进展。本文将聚焦于模型的自我提升能力(self-improvement)。 ...

如何优化大语言模型（LLM）的推理能力？

2024年，大语言模型在推理能力方面取得了显著突破。以O系列模型为例，在ARC-AGI评估任务中展现了令人瞩目的性能【1】： O3模型达到了87.5%的准确率，尽管每个任务的计算成本较高（超过$1,000）相比之下，未采用特殊推理技术的传统LLMs准确率通常低于25% Fig.1: O-Series Performance 如何通过有效的Prompting 来激发大语言模型的深层次推理能力，一直是研究者和开发者关注的核心问题。以下是几种主要的触发方法： ...