system architectureChapter 2NeurIPS 2023 · 2023
Describe, Explain, Plan and Select: Interactive Planning with Large Language Models
Zhengyao Jiang (UCL), Yingchen Xu (UCL)
Abstract
We present DEPS, a method for interactive planning with LLMs that uses a describe-explain-plan-select loop. DEPS enables agents to interactively refine plans based on execution feedback.
Key Contributions
- →DEPS interactive planning loop
- →Execution-feedback plan refinement
- →Describe-explain-plan-select cycle
Topics
interactive planningplan refinementfeedback loopsembodied agents
Relevance Scores
Long-Horizon Score87
Enterprise Score74
Completeness74
Paper Info
Year2023
VenueNeurIPS 2023
Typesystem architecture
ChapterCh. 2
Authors2
Related Papers
ReAct: Synergizing Reasoning and Acting in Language Mod…
2023 · Ch.1
Reflexion: Language Agents with Verbal Reinforcement Le…
2023 · Ch.1
Tree of Thoughts: Deliberate Problem Solving with Large…
2023 · Ch.1
Toolformer: Language Models Can Teach Themselves to Use…
2023 · Ch.1
View all Chapter 2 papers →