Research map / Large language models / Agents, code and math
Large Language Models as Commonsense Knowledge for Large-Scale Task Planning
Zirui Zhao, Wee Sun Lee, David Hsu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add LLM-induced commonsense world model and heuristic policy with MCTS vs UCT alone | MCTS · VirtualHome Seen Simple | success rate (%): 0.0 -> 91.4 | Improved |
| use LLM as heuristic in MCTS rather than as policy only | GPT3.5 Policy · VirtualHome Seen Comp. | success rate (%): 47.0 -> 71.2 | Improved |
| use LLM as heuristic in MCTS rather than as policy only | GPT3.5 Policy · VirtualHome Seen NovelComp.(3) | success rate (%): 5.4 -> 33.6 | Improved |
| GPT3.5-MCTS vs GPT3.5 policy on unseen apartment | GPT3.5 Policy · VirtualHome Unseen NovelComp.(3) | success rate (%): 6.9 -> 38.8 | Improved |
| GPT3.5-MCTS vs GPT3.5 policy on NovelComp.(2) unseen | GPT3.5 Policy · VirtualHome Unseen NovelComp.(2) | success rate (%): 54.0 -> 70.4 | Improved |
| add LLM heuristic policy (PUCT) to MCTS (ablation) | GPT3.5-MCTS · VirtualHome Seen Simple | success rate (%): 0.0 -> 91.4 | Improved |
| use LLM-generated commonsense state prior instead of uniform prior (ablation) | GPT3.5-MCTS · VirtualHome Seen Simple | success rate (%): 3.2 -> 91.4 | Improved |
| use LLM-generated commonsense state prior instead of uniform prior (ablation) | GPT3.5-MCTS · VirtualHome Seen Comp. | success rate (%): 0.0 -> 71.2 | Improved |
| give full observability instead of LLM commonsense belief (ablation) | GPT3.5-MCTS · VirtualHome Seen Simple | success rate (%): 91.4 -> 94.0 | Improved |
| give full observability instead of LLM commonsense belief (ablation) | GPT3.5-MCTS · VirtualHome Seen Comp. | success rate (%): 71.2 -> 80.7 | Improved |
| fine-tune GPT-2 policy vs few-shot GPT-3.5 policy | policy baseline · VirtualHome Seen NovelSimple | success rate (%): 74.3 -> 41.2 | Hurt |
| use LLM as world model with search instead of LLM as policy for flight planning | GPT-3.5 flight path prediction · Flight route planning | path accuracy | Improved |
Closest papers by meaning
- PlanU: Large Language Model Reasoning through Planning under Uncertainty (NeurIPS 2025 · similarity 0.90)
- SayCanPay: Heuristic Planning with Large Language Models Using Learnable Domain Knowledge (AAAI 2024 · similarity 0.90)
- Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning (AAAI 2024 · similarity 0.90)
- Graph-enhanced Large Language Models in Asynchronous Plan Reasoning (ICML 2024 · similarity 0.90)
- LLMs Can Plan Only If We Tell Them (ICLR 2025 · similarity 0.90)
- Thought of Search: Planning with Language Models Through The Lens of Efficiency (NeurIPS 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.
