Reasoning and planning
AI milestones in reasoning and planning, part of ai research.
6 milestones
OpenAI releases o1, a model trained to reason before answering
OpenAI released o1-preview and o1-mini on 12 September 2024, models trained by reinforcement learning to produce an extended chain of thought before answering. On the 2024 AIME examination GPT-4o averaged 12 per cent of problems; o1 averaged 74 per cent with a single attempt and 93 per cent when re-ranking a thousand samples.
Process supervision outperforms outcome supervision for LLM reasoning
Researchers showed that giving a model step-by-step feedback on its reasoning, rather than judging only the final answer, raised the solve rate to 78% on a representative subset of the MATH benchmark, and released 800,000 human feedback labels to support further work.
ReAct: LLMs learn to interleave reasoning traces and actions
Shunyu Yao and colleagues introduced ReAct, a method letting large language models interleave reasoning traces with real actions such as querying Wikipedia, reducing hallucination and outperforming prior methods on question answering, fact verification and interactive decision-making tasks.
Chain-of-thought prompting improves step-by-step reasoning in large language models
Jason Wei and colleagues showed that prompting a large language model with worked examples of intermediate reasoning steps dramatically improved its performance on arithmetic, commonsense, and symbolic tasks, reaching state-of-the-art accuracy on a maths benchmark.
Fifth Generation Computer Systems Project, Japan
In October 1981, Japan's Ministry of International Trade and Industry launched the Fifth Generation Computer Systems project, a ten-year state-funded programme delegated to the newly created Institute for New Generation Computer Technology (ICOT), aiming to build computers capable of logical inference, natural-language processing, and machine vision, with a budget of approximately 54 billion yen.
Meta-Level Knowledge in Expert Systems: Davis and Lenat's Formalisation at Stanford
In 1977, Randall Davis and Douglas Lenat at Stanford University published research formalising meta-level knowledge, a system's explicit representations of its own knowledge and reasoning strategies, and demonstrated its application in the MYCIN and AM expert systems to improve inference control and self-directed learning.