AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models

Chan Hee Song, Jiaman Wu, Clayton Washington, Brian M Sadler, Wei-Lun Chao, Yu Su

ICCV 2023 · Multi-agent systems and games › LLM agents · approach: Self-evolving language agent learning · 589 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add kNN retriever for in-context examples (ablation)LLM-Planner · LOOCV on 100 examplesHLP accuracy: 17.48 -> 40.59Improved
add logit biases favoring visible objects (ablation)LLM-Planner · LOOCV on 100 examplesHLP accuracy: 38.10 -> 40.59Improved
add grounded re-planning to static planning (ablation)LLM-Planner + HLSM · ALFRED Test Unseen (goal only)SR: 11.58 -> 13.41Improved
add grounded re-planning to static planning (ablation)LLM-Planner + HLSM · ALFRED Test Unseen (step-by-step)SR: 15.83 -> 16.42Improved
add grounded re-planning to static planning (ablation)LLM-Planner + HLSM · ALFRED Valid Unseen (step-by-step)SR: 14.26 -> 15.36Improved
use LLM-Planner few-shot instead of retraining HLSM high-level planner on 100 examplesHLSM · ALFRED Test Unseen (step-by-step)SR: 0.61 -> 16.42Improved
use generative LLM-Planner instead of SayCan rankingLLM-Planner · ALFRED Valid UnseenSR: 9.88 -> 15.36Improved
use generative planning instead of rankingLLM-Planner vs SayCan · GPT-3 calls per taskcalls: 22 -> 7Improved
increase training examples from 50 to 100 (ablation)LLM-Planner · ALFRED Valid UnseenSR: 10.06 -> 15.36Improved
increase training examples from 100 to 21k (ablation)LLM-Planner · ALFRED Valid UnseenSR: 15.36 -> 17.80Improved
increase training examples from 10k to 21kHLSM · ALFRED Valid UnseenSR: 9.51 -> 18.28Improved
increase in-context examples beyond 9 (ablation)LLM-Planner · LOOCV HLP accuracyHLP accuracyNo clear effect

Later papers that compared with this method

2 later accepted papers report LLM-Planner as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy