What's the Plan? Evaluating and Developing Planning-Aware Techniques for Language Models
Planning is a fundamental task in artificial intelligence that involves finding a sequence of actions that achieve a specified goal in a given environment. Large language models (LLMs) are increasingly used for applications that require planning capabilities, such as web or embodied agents. In line with recent studies, we demonstrate through experimentation that LLMs lack necessary skills required for planning. Based on these observations, we advocate for the potential of a hybrid approach that combines LLMs with classical planning methodology. Then, we introduce SimPlan, a novel hybrid-method, and evaluate its performance in a new challenging setup. Our extensive experiments across various planning domains demonstrate that SimPlan significantly outperforms existing LLM-based planners.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
World-aware Planning Narratives Enhance Large Vision-Language Model Planner
Large Vision-Language Models (LVLMs) show promise for embodied planning tasks but struggle with complex scenarios involving unfamiliar environments and multi-step goals. Current approaches rely on environment-agnostic im…
Imitation LearningLanguage ModelingLanguage ModellingSpatial Reasoning+1CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability. This neglects a crucial capability: agents' ability to devise and adju…
What if? Causal Machine Learning in Supply Chain Risk Management
The penultimate goal for developing machine learning models in supply chain management is to make optimal interventions. However, most machine learning models identify correlations in data rather than inferring causation…
Decision MakingManagementCATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning
Utilizing large language models (LLMs) for tool planning has emerged as a promising avenue for developing general AI systems, where LLMs automatically schedule external tools (e.g. vision models) to tackle complex tasks …
Balancing Explicability and Explanation in Human-Aware Planning
Human aware planning requires an agent to be aware of the intentions, capabilities and mental model of the human in the loop during its decision process. This can involve generating plans that are explicable to a human o…
Decision MakingExplanation GenerationTask Planning