AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models

Siqi Ouyang, Lei Li
5/24/2023
cs.CL

Official code: owaski/AutoPlan (3 stars, MIT, last commit 2023-06-24).

Abstract

Recent large language models (LLMs) are promising for making decisions in grounded environments. However, LLMs frequently fail in complex decision-making tasks due to the misalignment between the pre-trained knowledge in LLMs and the actual rules in the environment. Existing methods require either costly gradient computation or lengthy in-context demonstrations. In this paper, we propose AutoPlan, an approach to guide LLM-based agents to accomplish interactive decision-making tasks. AutoPlan augments the LLM prompt with a task-solving plan and optimizes it through iterative experience collection and reflection. Our experiments show that AutoPlan, though using no in-context demonstrations, achieves success rates on par with the baselines using human-written demonstrations on ALFWorld and even outperforms them by 8% on HotpotQA. The code is available at https://github.com/owaski/AutoPlan.

View on arXivView PDF

Code Implementations(1)

owaski/AutoPlanOfficial100%
MIT

The code repo of paper "AutoPlan"

31PythonJun 24, 20233 years agoMIT

Similar Papers

ExpeL: LLM Agents Are Experiential Learners

88% match1 repo2262023

Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach

87% match1 repo812023

WESE: Weak Exploration to Strong Exploitation for LLM Agents

87% match2024

O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models

86% match2023

Scaling Autonomous Agents via Automatic Reward Modeling And Planning

86% match2026

Introspective Tips: Large Language Model for In-Context Decision Making

86% match2023

Cite this paper

@article{ouyang2023autoplan,
  title  = {AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models},
  author = {Siqi Ouyang and Lei Li},
  year   = {2023},
  eprint = {2305.15064},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.15064v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.15064.svg)](https://codeofpaper.com/paper/2305.15064)

Discussion