Supervised fine-tuning lets LLMs linearly encode action validity and state predicates, with broader state-space coverage during training improving world-model recovery.
What’s the plan? evaluating and developing planning- aware techniques for llms.arXiv preprint arXiv:2402.11489,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Hybrid LLM-SMT assistance system for capability-based planning that supports natural-language interaction, result interpretation, and iterative knowledge-model adaptation under human approval.
citing papers explorer
-
A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners
Supervised fine-tuning lets LLMs linearly encode action validity and state predicates, with broader state-space coverage during training improving world-model recovery.
-
An LLM-Based Assistance System for Intuitive and Flexible Capability-Based Planning
Hybrid LLM-SMT assistance system for capability-based planning that supports natural-language interaction, result interpretation, and iterative knowledge-model adaptation under human approval.
- Verbalized Algorithms: Classical Algorithms are All You Need (Mostly)