Plan-over-Graph: Towards Parallelable LLM Agent Schedule
Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning. However, challenges remain under-explored for parallel schedules. This paper introduces a novel paradigm, plan-over-graph, in which the model first decomposes a real-life textual task into executable subtasks and constructs an abstract task graph. The model then understands this task graph as input and generates a plan for parallel execution. To enhance the planning capability of complex, scalable graphs, we design an automated and controllable pipeline to generate synthetic graphs and propose a two-stage training scheme. Experimental results show that our plan-over-graph method significantly improves task performance on both API-based LLMs and trainable open-sourced LLMs. By normalizing complex tasks as graphs, our method naturally supports parallel execution, demonstrating global efficiency. The code and data are available at https://github.com/zsq259/Plan-over-Graph.
Code (1)
Tasks
Task PlanningSimilar Papers 제목 키워드 기반
Graph neural networks-based Scheduler for Production planning problems using Reinforcement Learning
Reinforcement learning (RL) is increasingly adopted in job shop scheduling problems (JSSP). But RL for JSSP is usually done using a vectorized representation of machine features as the state space. It has three major pro…
Distributed OptimizationGraph Neural NetworkJob Shop Schedulingreinforcement-learning+2From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Execution
The dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to do next by reading an ever growing context window. This paradigm has three structura…
A Novel Multi-Agent Scheduling Mechanism for Adaptation of Production Plans in Case of Supply Chain Disruptions
Manufacturing companies typically use sophisticated production planning systems optimizing production steps, often delivering near-optimal solutions. As a downside for delivering a near-optimal schedule, planning systems…
SchedulingScheduleNet: Learn to solve multi-agent scheduling problems with reinforcement learning
We propose ScheduleNet, a RL-based real-time scheduler, that can solve various types of multi-agent scheduling problems. We formulate these problems as a semi-MDP with episodic reward (makespan) and learn ScheduleNet, a …
Decision MakingGraph AttentionJob Shop Schedulingreinforcement-learning+2Explaining Preference-driven Schedules: the EXPRES Framework
Scheduling is the task of assigning a set of scarce resources distributed over time to a set of agents, who typically have preferences about the assignments they would like to get. Due to the constrained nature of these …
Scheduling