LLMs by themselves are not perfect zero-shot solvers and can sometimes misinterpret or insufficiently describe the dynamics of an environment. CLIMB empowers these systems to explore, identify, and correct these biases to solve complex tasks.

[5/6]

We develop BlocksWorld++, a curriculum of block stacking and manipulation tasks that showcases CLIMB’s ability to generalize and reuse task primitives. We implemented BlocksWorld++ in logical PDDL, IsaacSim, and a real tabletop environment to enable evaluations at multiple levels of fidelity.

[4/6]

We are thrilled to announce that our paper, Language-Guided Continual Learning for Task Planning with Iterative Model Building (CLIMB), was accepted to #ICRA2025!

CLIMB is a robot task planner that builds a world model by iteratively executing and observing tasks.

📃 plan-with-climb.github.io
[1/6]