A Knowledge Reasoning Algorithm Based on Network Structure and Representation Learning

Yao, Jinkui; Zhao, Yulong

doi:10.1109/icicn51133.2020.9205073

Cited by 1 publication

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By actively engaging with the environment and utilizing feedback, extrospective reasoning offers a more flexible and responsive approach to generating plans, which is particularly suitable for complex and dynamic situations where the ability to adapt and learn from experience is crucial. Several related works in the field of extrospective reasoning with LLMs include Self-Ask (Press et al, 2023), ReAct (Yao et al, 2023c), ToolFormer (Schick et al, 2023), and LLM-Planner (Song et al, 2023a). Self-Ask (Press et al, 2023) proactively generates and responds to its own follow-up queries before addressing the original question.…”

Section: Extrospective Reasoningmentioning

confidence: 99%

“…Self-Ask (Press et al, 2023) proactively generates and responds to its own follow-up queries before addressing the original question. Meanwhile, ReAct (Yao et al, 2023c) leverages large language models to concurrently produce reasoning traces and task-specific actions. This dual approach enhances the interaction between these elements, with reasoning traces aiding in the development, monitoring, and modification of action plans, as well as managing unexpected situations.…”

Section: Extrospective Reasoningmentioning

confidence: 99%

“…AutoGPT (gravitas/auto gpt, 2023) decomposes problems into subproblems and employs tools to solve them. ReAct (Yao et al, 2023c) explores the interleaved generation of reasoning traces and task-specific actions for enhanced synergy in language tasks, improving interpretability and trustworthiness. Reflexion (Shinn et al, 2023) reinforces language agents through linguistic feedback and episodic memory, improving decision-making in subsequent trials.…”

Section: Autonomous Agentmentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Reasoning with Foundation Models

Sun,

Zheng,

Xie

et al. 2023

Preprint

View full text Add to dashboard Cite

https://github.com/reasoning-survey/Awesome-Reasoning-Foundation-Models Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-world settings such as negotiation, medical diagnosis, and criminal investigation. It serves as a fundamental methodology in the field of Artificial General Intelligence (AGI). With the ongoing development of foundation models, there is a growing interest in exploring their abilities in reasoning tasks. In this paper, we introduce seminal foundation models proposed or adaptable for reasoning, highlighting the latest advancements in various reasoning tasks, methods, and benchmarks. We then delve into the potential future directions behind the emergence of reasoning abilities within foundation models. We also discuss the relevance of multimodal learning, autonomous agents, and super alignment in the context of reasoning. By discussing these future research directions, we hope to inspire researchers in their exploration of this field, stimulate further advancements in reasoning with foundation models, and contribute to the development of AGI.

show abstract

Section: Extrospective Reasoningmentioning

confidence: 99%

Section: Extrospective Reasoningmentioning

confidence: 99%

Section: Autonomous Agentmentioning

confidence: 99%

See 1 more Smart Citation