An iterative code-generation framework (IPP) improves LLM performance on GRASP and MiniGrid grid-planning tasks by refining generated policy programs based on execution feedback.
IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present the IGLU Gridworld: a reinforcement learning environment for building and evaluating language conditioned embodied agents in a scalable way. The environment features visual agent embodiment, interactive learning through collaboration, language conditioned RL, and combinatorically hard task (3d blocks building) space.
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Code-Driven Planning in Grid Worlds with Large Language Models
An iterative code-generation framework (IPP) improves LLM performance on GRASP and MiniGrid grid-planning tasks by refining generated policy programs based on execution feedback.