Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future
Zheng Chu, Jingchang Chen, Qianglong Chen, Weijiang Yu, Tao He, Haotian Wang, Weihua Peng, Ming Liu, Bing Qin, Ting Liu
摘要
Reasoning, a fundamental cognitive process integral to human intelligence, has garnered substantial interest within artificial intelligence. Notably, recent studies have revealed that chainof-thought prompting significantly enhances LLM's reasoning capabilities, which attracts widespread attention from both academics and industry. In this paper, we systematically investigate relevant research, summarizing advanced methods through a meticulous taxonomy that offers novel perspectives. Moreover, we delve into the current frontiers and delineate the challenges and future directions, thereby shedding light on future research. Furthermore, we engage in a discussion about open questions. We hope this paper serves as an introduction for beginners and fosters future research. Resources have been made publicly available at https://github.com/zchuz/CoT-Reasoning-Survey .
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper53
- AgentAuditor: Human-level Safety and Security Evaluation for LLM AgentsHanjun Luo, Shenyu Dai, Chiming Ni, Xinfeng Li 等NeurIPS 2025 · 被引用 98 次
- Contextual Integrity in LLMs via Reasoning and Reinforcement LearningGuangchen Lan, Huseyin A. Inan, Sahar Abdelnabi, Janardhan Kulkarni 等NeurIPS 2025 · 被引用 56 次
- LlaVA-CoT: Let Vision Language Models Reason Step-By-StepGuowei Xu, Peng Jin, Ziang Wu, Hao Li 等ICCV 2025 · 被引用 37 次
- ACPBench: Reasoning About Action, Change, and PlanningHarsha Kokel, Michael Katz, Kavitha Srinivas, Shirin SohrabiAAAI 2025 · 被引用 35 次
- VisualWebInstruct: Scaling up Multimodal Instruction Data through Web SearchYiming Jia, Jiachen Li, Xiang Yue, Bo Li 等EMNLP 2025 · 被引用 29 次
它引用的顶会 Paper88
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah 等NeurIPS 2020 · 被引用 64,255 次
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma 等NeurIPS 2022 · 被引用 22,562 次
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn 等ICLR 2021 · 被引用 21,477 次
- Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo 等NeurIPS 2022 · 被引用 8,168 次
- Flamingo: a Visual Language Model for Few-Shot LearningJean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech 等NeurIPS 2022 · 被引用 6,707 次
相关 Paper
- To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningZayne Rea Sprague, Fangcong Yin, Juan Diego Rodriguez, Dongwei Jiang 等ICLR 2025
- Revealing the Seen, Imagining the Beyond: A Survey of Image-Grounded Chain-of-Thought Reasoning in Multimodal LLMsQihua Dong, Yitian Zhang, Huimin Zeng, Yizhou Wang 等ACL 2026
- Unveiling Factual Recall Behaviors of Large Language Models through Knowledge NeuronsYifei Wang, Yuheng Chen, Wanting Wen, Yu Sheng 等EMNLP 2024 · 被引用 3 次
- Reasoning with Language Model Prompting: A SurveyShuofei Qiao, Yixin Ou, Ningyu Zhang, Xiang Chen 等ACL 2023 · 被引用 124 次
- Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-ThoughtQiguang Chen, Libo Qin, Jiaqi Wang, Jingxuan Zhou 等NeurIPS 2024 · 被引用 104 次
