Research map / Large language models / Agents, code and math
Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use an LLM-acquired PDDL model with Fast Downward instead of an LLM planner alone | Task planning · Household | success rate: 15% -> 95% | Helped |
| Use an LLM-acquired PDDL model with Fast Downward instead of an LLM planner alone | Task planning · Logistics | success rate: 0% -> 100% | Helped |
| Add VAL validation feedback to LLM-generated plans | LLM planner · Household | success rate: 15% -> 48% | Helped |
| Add VAL validation feedback to LLM-generated plans | LLM planner · Logistics | success rate: 0% -> 33% | Helped |
| Use GPT-4 rather than GPT-3.5-Turbo to construct PDDL models | PDDL construction · Household | number of errors: 218+ -> 53 | Helped |
| Use GPT-4 rather than GPT-3.5-Turbo to construct PDDL models | PDDL construction · Logistics | number of errors: 38 -> 2 | Helped |
| Use GPT-4 rather than GPT-3.5-Turbo to construct PDDL models | PDDL construction · Tyreworld | number of errors: 94+ -> 4 | Helped |
| Correct PDDL model errors using natural-language expert feedback | GPT-4-generated PDDL · Household and IPC domains | factual errors corrected: 59 feedback messages to address 56 factual errors | Helped |
Closest papers by meaning
- Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models (NeurIPS 2024 · similarity 0.95)
- Large Language Models as Planning Domain Generators (Student Abstract) (AAAI 2024 · similarity 0.91)
- Generalized Planning in PDDL Domains with Pretrained Large Language Models (AAAI 2024 · similarity 0.90)
- LLMs Can Plan Only If We Tell Them (ICLR 2025 · similarity 0.90)
- Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks (ICML 2025 · similarity 0.90)
- SayCanPay: Heuristic Planning with Large Language Models Using Learnable Domain Knowledge (AAAI 2024 · similarity 0.89)
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.