Interactive and Expressive Code-Augmented Planning with Large Language Models
- URL: http://arxiv.org/abs/2411.13826v1
- Date: Thu, 21 Nov 2024 04:23:17 GMT
- Title: Interactive and Expressive Code-Augmented Planning with Large Language Models
- Authors: Anthony Z. Liu, Xinhe Wang, Jacob Sansom, Yao Fu, Jongwook Choi, Sungryull Sohn, Jaekyeom Kim, Honglak Lee,
- Abstract summary: Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making.
Recent techniques have sought to structure LLM outputs using control flow and other code-adjacent techniques to improve planning performance.
We propose REPL-Plan, an LLM planning approach that is fully code-expressive and dynamic.
- Score: 62.799579304821826
- License:
- Abstract: Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making, but often struggle with complex, long-horizon planning tasks. Recent techniques have sought to structure LLM outputs using control flow and other code-adjacent techniques to improve planning performance. These techniques include using variables (to track important information) and functions (to divide complex tasks into smaller re-usable sub-tasks). However, purely code-based approaches can be error-prone and insufficient for handling ambiguous or unstructured data. To address these challenges, we propose REPL-Plan, an LLM planning approach that is fully code-expressive (it can utilize all the benefits of code) while also being dynamic (it can flexibly adapt from errors and use the LLM for fuzzy situations). In REPL-Plan, an LLM solves tasks by interacting with a Read-Eval-Print Loop (REPL), which iteratively executes and evaluates code, similar to language shells or interactive code notebooks, allowing the model to flexibly correct errors and handle tasks dynamically. We demonstrate that REPL-Plan achieves strong results across various planning domains compared to previous methods.
Related papers
- Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning [94.76546523689113]
We introduce CodePlan, a framework that generates and follows textcode-form plans -- pseudocode that outlines high-level, structured reasoning processes.
CodePlan effectively captures the rich semantics and control flows inherent to sophisticated reasoning tasks.
It achieves a 25.1% relative improvement compared with directly generating responses.
arXiv Detail & Related papers (2024-09-19T04:13:58Z) - Scaling Up Natural Language Understanding for Multi-Robots Through the Lens of Hierarchy [8.180994118420053]
Long-horizon planning is hindered by challenges such as uncertainty accumulation, computational complexity, delayed rewards and incomplete information.
This work proposes an approach to exploit the task hierarchy from human instructions to facilitate multi-robot planning.
arXiv Detail & Related papers (2024-08-15T14:46:13Z) - Exploring and Benchmarking the Planning Capabilities of Large Language Models [57.23454975238014]
This work lays the foundations for improving planning capabilities of large language models (LLMs)
We construct a comprehensive benchmark suite encompassing both classical planning benchmarks and natural language scenarios.
We investigate the use of many-shot in-context learning to enhance LLM planning, exploring the relationship between increased context length and improved planning performance.
arXiv Detail & Related papers (2024-06-18T22:57:06Z) - Sub-goal Distillation: A Method to Improve Small Language Agents [21.815417165548187]
Large Language Models (LLMs) have demonstrated significant promise as agents in interactive tasks.
We propose a method for transferring the performance of an LLM with billions of parameters to a much smaller language model.
In ScienceWorld, a challenging and multi-task interactive text environment, our method surpasses standard imitation learning based solely on elementary actions by 16.7%.
arXiv Detail & Related papers (2024-05-04T20:34:06Z) - If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code
Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
Large language models (LLMs) are trained on a combination of natural language and formal language (code)
Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
arXiv Detail & Related papers (2024-01-01T16:51:20Z) - ADaPT: As-Needed Decomposition and Planning with Language Models [131.063805299796]
We introduce As-Needed Decomposition and Planning for complex Tasks (ADaPT)
ADaPT explicitly plans and decomposes complex sub-tasks as-needed, when the Large Language Models is unable to execute them.
Our results demonstrate that ADaPT substantially outperforms established strong baselines.
arXiv Detail & Related papers (2023-11-08T17:59:15Z) - Improving Planning with Large Language Models: A Modular Agentic Architecture [7.63815864256878]
Large language models (LLMs) often struggle with tasks that require multi-step reasoning or goal-directed planning.
We propose an agentic architecture, the Modular Agentic Planner (MAP), in which planning is accomplished via the recurrent interaction of specialized modules.
We find that MAP yields significant improvements over both standard LLM methods.
arXiv Detail & Related papers (2023-09-30T00:10:14Z) - Dynamic Planning with a LLM [15.430182858130884]
Large Language Models (LLMs) can solve many NLP tasks in zero-shot settings, but applications involving embodied agents remain problematic.
Our work presents LLM Dynamic Planner (LLM-DP), a neuro-symbolic framework where an LLM works hand-in-hand with a traditional planner to solve an embodied task.
arXiv Detail & Related papers (2023-08-11T21:17:13Z) - Learning to Plan with Natural Language [111.76828049344839]
Large Language Models (LLMs) have shown remarkable performance in various basic natural language tasks.
For completing the complex task, we still need a plan for the task to guide LLMs to generate the specific solutions step by step.
We propose the Learning to Plan method, which involves two phases: (1) In the first learning task plan phase, it iteratively updates the task plan with new step-by-step solutions and behavioral instructions, which are obtained by prompting LLMs to derive from training error feedback.
arXiv Detail & Related papers (2023-04-20T17:09:12Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.