6 papers · 1 filter
Symmetry-Aware Transformer Training for Automated Planning
Markus Fritzsche, Elliot Gestrin, Jendrik Seipp
While transformers excel in many settings, their application in the field of automated planning is limited. Prior work like PlanGPT, a state-of-the-art decoder-only transformer, st…
Frontier Large Language Models Rival State-of-the-Art Planners
Augusto B. Corrêa, André G. Pereira, Jendrik Seipp
A series of influential studies established that large language models cannot reliably solve even simple planning tasks. We show that the latest generation of frontier models overt…
Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code
Augusto B. Corrêa, André G. Pereira, Jendrik Seipp
In recent years, large language models (LLMs) have shown remarkable capabilities in various artificial intelligence problems. However, they fail to plan reliably, even when prompte…
NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions
Elliot Gestrin, Marco Kuhlmann, Jendrik Seipp
Classical planners are powerful systems, but modeling tasks in input formats such as PDDL is tedious and error-prone. In contrast, planning with Large Language Models (LLMs) allows…
Numeric Reward Machines
Kristina Levina, Nikolaos Pappas, Athanasios Karapantelakis +2
Reward machines inform reinforcement learning agents about the reward structure of the environment and often drastically speed up the learning process. However, reward machines onl…
Consolidating LAMA with Best-First Width Search
Augusto B. Corrêa, Jendrik Seipp
One key decision for heuristic search algorithms is how to balance exploration and exploitation. In classical planning, novelty search has come out as the most successful approach…