AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Natural Language PDDL (NL-PDDL) for Open-world Goal-oriented Commonsense Regression Planning in Embodied AI

Xiaotian Liu, Armin Toroghi, Jiazhou Liang, David Courtis, Ruiwen Li, Ali Pesaranghader, Jaehong Kim, Tanmana Sadhu, Hyejeong Jeon, Scott Sanner

ICLR 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning

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
use NL-PDDL lifted regression instead of ReAct (w examples)ALFWorld Text planner · ALFWorld Textsuccess rate (%): 81% -> 94%Improved
use NL-PDDL instead of ReAct in token costALFWorld Text planner · ALFWorld Text# tokens: 5,507,266 -> 443,407Improved
use NL-PDDL instead of fine-tuned EMMA-10ALFWorld Vision planner · ALFWorld Visionsuccess rate (%): 82% -> 84%Improved
use NL-PDDL instead of direct GPT-4oALFWorld Vision planner · ALFWorld Visionsuccess rate (%): 8% -> 84%Improved
use NL-PDDL instead of direct LLM planners on Mystery BlocksworldBlocksworld planner · Mystery Blocksworldsuccess rate (%): 0% -> 70%Improved
use classical Fast Downward instead of NL-PDDL on aligned BlocksworldBlocksworld planner · Blocksworldsuccess rate (%): 70% -> 100%Hurt
introduce goal-action misalignmentNL-PDDL · ALFWorld Textsuccess rate (%): 94% -> 91%Hurt
introduce goal-action misalignmentNL-PDDL · ALFWorld Visionsuccess rate (%): 84% -> 80%Hurt
introduce goal-action misalignmentNL-PDDL · Blocksworldsuccess rate (%): 70% -> 70%No clear effect
introduce goal-action misalignmentReAct (w examples) · ALFWorld Textsuccess rate (%): 81% -> 79%Hurt
introduce goal-action misalignmentFast Downward · Blocksworldsuccess rate (%): 100% -> 0%Hurt
increase optimal plan depth beyond 6NL-PDDL · Blocksworldsuccess rate (%): 100% -> 84%Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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