Self-reflection is a vital aspect that allows autonomous agents to improve iteratively by refining past action decisions and correcting previous mistakes. Essentially, the planning step is outsourced to an external tool, assuming the availability of domain-specific PDDL and a suitable planner which is common in certain robotic setups but not in many other domains. In this process, LLM (1) translates the problem into “Problem PDDL”, then (2) requests a classical planner to generate a PDDL plan based on an existing “Domain PDDL”, and finally (3) translates the PDDL plan back into natural language. This approach utilizes the Planning Domain Definition Language (PDDL) as an intermediate interface to describe the planning problem. 2023), involves relying on an external classical planner to do long-horizon planning. "Write a story outline." for writing a novel, or (3) with human inputs.Īnother quite distinct approach, LLM+P ( Liu et al. Task decomposition can be done (1) by LLM with simple prompting like "Steps for XYZ.\n1.", "What are the subgoals for achieving XYZ?", (2) by using task-specific instructions e.g. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. 2023) extends CoT by exploring multiple reasoning possibilities at each step. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. Task Decomposition #Ĭhain of thought (CoT Wei et al. An agent needs to know what they are and plan ahead. Component One: Planning #Ī complicated task usually involves many steps. Overview of a LLM-powered autonomous agent system.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |