A survey on large language model based autonomous agents

L Wang, C Ma, X Feng, Z Zhang, H Yang… - Frontiers of Computer …, 2024 - Springer
Autonomous agents have long been a research focus in academic and industry
communities. Previous research often focuses on training agents with limited knowledge …

When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs

R Kamoi, Y Zhang, N Zhang, J Han… - Transactions of the …, 2024 - direct.mit.edu
Self-correction is an approach to improving responses from large language models (LLMs)
by refining the responses using LLMs during inference. Prior work has proposed various self …

Reflexion: Language agents with verbal reinforcement learning

N Shinn, F Cassano, A Gopinath… - Advances in …, 2024 - proceedings.neurips.cc
Large language models (LLMs) have been increasingly used to interact with external
environments (eg, games, compilers, APIs) as goal-driven agents. However, it remains …

Graph of thoughts: Solving elaborate problems with large language models

M Besta, N Blach, A Kubicek, R Gerstenberger… - Proceedings of the …, 2024 - ojs.aaai.org
Abstract We introduce Graph of Thoughts (GoT): a framework that advances prompting
capabilities in large language models (LLMs) beyond those offered by paradigms such as …

Reasoning with language model is planning with world model

S Hao, Y Gu, H Ma, JJ Hong, Z Wang, DZ Wang… - arxiv preprint arxiv …, 2023 - arxiv.org
Large language models (LLMs) have shown remarkable reasoning capabilities, especially
when prompted to generate intermediate reasoning steps (eg, Chain-of-Thought, CoT) …

Large language models cannot self-correct reasoning yet

J Huang, X Chen, S Mishra, HS Zheng, AW Yu… - arxiv preprint arxiv …, 2023 - arxiv.org
Large Language Models (LLMs) have emerged as a groundbreaking technology with their
unparalleled text generation capabilities across various applications. Nevertheless …

Deductive verification of chain-of-thought reasoning

Z Ling, Y Fang, X Li, Z Huang, M Lee… - Advances in …, 2024 - proceedings.neurips.cc
Abstract Large Language Models (LLMs) significantly benefit from Chain-of-thought (CoT)
prompting in performing various reasoning tasks. While CoT allows models to produce more …

Reasoning with language model prompting: A survey

S Qiao, Y Ou, N Zhang, X Chen, Y Yao, S Deng… - arxiv preprint arxiv …, 2022 - arxiv.org
Reasoning, as an essential ability for complex problem-solving, can provide back-end
support for various real-world applications, such as medical diagnosis, negotiation, etc. This …

Bridging the gap: A survey on integrating (human) feedback for natural language generation

P Fernandes, A Madaan, E Liu, A Farinhas… - Transactions of the …, 2023 - direct.mit.edu
Natural language generation has witnessed significant advancements due to the training of
large language models on vast internet-scale datasets. Despite these advancements, there …

Self-evaluation guided beam search for reasoning

Y **e, K Kawaguchi, Y Zhao, JX Zhao… - Advances in …, 2024 - proceedings.neurips.cc
Breaking down a problem into intermediate steps has demonstrated impressive
performance in Large Language Model (LLM) reasoning. However, the growth of the …