AI Paper Atlas

Research map / Large language models / Agents, code and math

One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration

Jinbang Huang, Yixin Xiao, Zhanguang Zhang, Mark Coates, Jianye HAO, Yingxue Zhang

ICLR 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents · 11 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 symbolic PDDL solver instead of using the domain as LLM memory (ablation)PDDLLM · Nine PyBullet TAMP tasks, overall (50 s limit)planning success rate (%): 69.9 -> 93.3Improved
add failure feedback loop to LLMTAMPLLMTAMP · Nine PyBullet TAMP tasks, overall (50 s limit)planning success rate (%): 35.7 -> 52.5Improved
add failure reasons to replanning (LLMTAMP-FR)LLMTAMP · Nine PyBullet TAMP tasks, overall (50 s limit)planning success rate (%): 35.7 -> 48.6Improved
replace GPT-4o with o1 reasoning modelLLMTAMP · Rearrangement/Hanoi/Bridge, extended limitplanning success rate (%): 13.9 -> 61.5Improved
replace GPT-4o with DeepSeek R1 reasoning modelLLMTAMP · Rearrangement/Hanoi/Bridge, extended limitplanning success rate (%): 13.9 -> 35.9Improved
use derived PDDL domain instead of o1 reasoning plannerPDDLLM vs o1-TAMP · Rearrangement/Hanoi/Bridge, extended limittoken cost (k): 666 -> 415Improved
add pick demonstration only (ablation)PDDLLM · Bridge Building, demonstrationplanning success rate (%): 0.0 -> 20.0 with pick and stack addedHurt
add align demonstration to pick and stack (ablation)PDDLLM · Bridge Building, demonstrationplanning success rate (%): 20.0 -> 86.7Improved
add redundant unstack demonstration (ablation)PDDLLM · Bridge Building, demonstrationplanning success rate (%): 86.7 -> 83.3No clear effect
use 5 instead of 10 parallel prompts (ablation)PDDLLM · Unstackplanning success rate (%): 97.8% -> 100%No clear effect
use 5 instead of 10 parallel prompts (ablation)PDDLLM · Stackplanning success rate (%): 97.8% -> 96.1%No clear effect
shuffle order of dimensions in prompt (ablation)PDDLLM · Stackplanning success rate (%): 97.8% -> 96.1%No clear effect

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