ArXiv TLDR

Karthik Narasimhan

2 papers · Latest:

Natural Language Processing

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Tree of Thoughts (ToT) is a novel inference framework that enables large language models to perform strategic, multi-step problem solving by exploring multiple reasoning paths and backtracking when needed.

2305.10601
Natural Language Processing

ReAct: Synergizing Reasoning and Acting in Language Models

ReAct is a method that interleaves reasoning and acting in language models to improve task-solving accuracy and interpretability by enabling interaction with external environments.

2210.03629

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.