A survey on large language model based autonomous agents
Autonomous agents have long been a research focus in academic and industry
communities. Previous research often focuses on training agents with limited knowledge …
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
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 …
by refining the responses using LLMs during inference. Prior work has proposed various self …
Reflexion: Language agents with verbal reinforcement learning
Large language models (LLMs) have been increasingly used to interact with external
environments (eg, games, compilers, APIs) as goal-driven agents. However, it remains …
environments (eg, games, compilers, APIs) as goal-driven agents. However, it remains …
Graph of thoughts: Solving elaborate problems with large language models
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 …
capabilities in large language models (LLMs) beyond those offered by paradigms such as …
Reasoning with language model is planning with world model
Large language models (LLMs) have shown remarkable reasoning capabilities, especially
when prompted to generate intermediate reasoning steps (eg, Chain-of-Thought, CoT) …
when prompted to generate intermediate reasoning steps (eg, Chain-of-Thought, CoT) …
Large language models cannot self-correct reasoning yet
Large Language Models (LLMs) have emerged as a groundbreaking technology with their
unparalleled text generation capabilities across various applications. Nevertheless …
unparalleled text generation capabilities across various applications. Nevertheless …
Deductive verification of chain-of-thought reasoning
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 …
prompting in performing various reasoning tasks. While CoT allows models to produce more …
Reasoning with language model prompting: A survey
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 …
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
Natural language generation has witnessed significant advancements due to the training of
large language models on vast internet-scale datasets. Despite these advancements, there …
large language models on vast internet-scale datasets. Despite these advancements, there …
Self-evaluation guided beam search for reasoning
Breaking down a problem into intermediate steps has demonstrated impressive
performance in Large Language Model (LLM) reasoning. However, the growth of the …
performance in Large Language Model (LLM) reasoning. However, the growth of the …