Thinking Machines: A Survey of LLM based Reasoning Strategies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bandyopadhyay, Dibyanayan, Bhattacharjee, Soham, Ekbal, Asif
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915197338255360
author Bandyopadhyay, Dibyanayan
Bhattacharjee, Soham
Ekbal, Asif
author_facet Bandyopadhyay, Dibyanayan
Bhattacharjee, Soham
Ekbal, Asif
contents Large Language Models (LLMs) are highly proficient in language-based tasks. Their language capabilities have positioned them at the forefront of the future AGI (Artificial General Intelligence) race. However, on closer inspection, Valmeekam et al. (2024); Zecevic et al. (2023); Wu et al. (2024) highlight a significant gap between their language proficiency and reasoning abilities. Reasoning in LLMs and Vision Language Models (VLMs) aims to bridge this gap by enabling these models to think and re-evaluate their actions and responses. Reasoning is an essential capability for complex problem-solving and a necessary step toward establishing trust in Artificial Intelligence (AI). This will make AI suitable for deployment in sensitive domains, such as healthcare, banking, law, defense, security etc. In recent times, with the advent of powerful reasoning models like OpenAI O1 and DeepSeek R1, reasoning endowment has become a critical research topic in LLMs. In this paper, we provide a detailed overview and comparison of existing reasoning techniques and present a systematic survey of reasoning-imbued language models. We also study current challenges and present our findings.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10814
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Thinking Machines: A Survey of LLM based Reasoning Strategies
Bandyopadhyay, Dibyanayan
Bhattacharjee, Soham
Ekbal, Asif
Computation and Language
Large Language Models (LLMs) are highly proficient in language-based tasks. Their language capabilities have positioned them at the forefront of the future AGI (Artificial General Intelligence) race. However, on closer inspection, Valmeekam et al. (2024); Zecevic et al. (2023); Wu et al. (2024) highlight a significant gap between their language proficiency and reasoning abilities. Reasoning in LLMs and Vision Language Models (VLMs) aims to bridge this gap by enabling these models to think and re-evaluate their actions and responses. Reasoning is an essential capability for complex problem-solving and a necessary step toward establishing trust in Artificial Intelligence (AI). This will make AI suitable for deployment in sensitive domains, such as healthcare, banking, law, defense, security etc. In recent times, with the advent of powerful reasoning models like OpenAI O1 and DeepSeek R1, reasoning endowment has become a critical research topic in LLMs. In this paper, we provide a detailed overview and comparison of existing reasoning techniques and present a systematic survey of reasoning-imbued language models. We also study current challenges and present our findings.
title Thinking Machines: A Survey of LLM based Reasoning Strategies
topic Computation and Language
url https://arxiv.org/abs/2503.10814