Task Decomposition

Follow this topic Ask about this topic

Task decomposition asks how to break a complex goal into subtasks, order them by dependency, and decide which people, agents, or tools should handle each part. Approaches include hierarchical task networks, dependency graphs and abstract syntax trees, recursive language-model planning, skill retrieval, and reinforcement learning, sometimes paired with formal checks or executable tests. These methods are used in settings such as mathematics, coding, database queries, robotics, and long-horizon research, where smaller steps can make work easier to verify, delegate, or reuse. A central tension is choosing the right granularity: decomposition can improve accuracy and control, but extra coordination, bad boundaries, and repeated downstream work can raise costs or reduce success.

Latest papers

37 papers7 papers in the last four weeks, down 12% on the four weeks before. 0.0% of all new papers.

Reward Shaping and Action Masking for Compositional Tasks using Behavior Trees and LLMs
May 7, 2026Nicholas Potteiger, Ankita Samaddar, Taylor T. Johnson +1Reinforcement Learning Reward Shaping
Vanderbilt University, Nashville, TN
Mise en Place for Agentic Coding: Deliberate Preparation as Context Engineering Methodology
May 6, 2026Andrew ZiglerLLM Planning Agentic Code Generation
LinearB Los Angeles, USA
Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
May 6, 2026Zhiqing Cui, Haotong Xie, Jiahao Yuan +11Multi-Agent System Optimization Multi-Agent Orchestration
Project lead.
Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks
Feb 26, 2026Kunihiro Miyazaki, Takanobu Kawahara, Stephen Roberts +1Multi-Agent LLM Systems Algorithmic Trading
Japan Digital Design, Inc. Tokyo, Japan · Department of Engineering Science University of Oxford United Kingdom
Learning to Solve Complex Problems via Dataset Decomposition
Feb 23, 2026Wanru Zhao, Lucas Caccia, Zhengyan Shi +3Curriculum Learning Training Data Curation
University of Cambridge · Microsoft Research · Mila - Quebec AI Institute
Beyond the Prompt in Large Language Models: Comprehension, In-Context Learning, and Chain-of-Thought
Feb 16, 2026Yuling Jiao, Yanming Lai, Huazhen Lin +3LLM Prompting In-Context Learning
School of Artificial Intelligence, Wuhan University · National Center for Applied Mathematics in Hubei, Wuhan University · Hubei Key Laboratory of Computational Science, Wuhan University +6
LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models
Apr 3, 2025Weibin Liao, Xin Gao, Tianyu Jia +6LLM Planning RL for Language Model Reasoning
School of Computer Science, Peking University · 2Key Laboratory of High Confidence Software Technologies, Ministry of Education · School of Computer Sciences, Beijing University of Posts and Telecommunications +5

May 7, 2026J/K move · Enter open · S save

Reward Shaping and Action Masking for Compositional Tasks using Behavior Trees and LLMs

Nicholas Potteiger, Ankita Samaddar, Taylor T. Johnson, Xenofon Koutsoukos

Vanderbilt University, Nashville, TN

Reinforcement Learning Reward Shaping LLM-Guided RL Task Decomposition Reward Design for RL

Open paper AskPDF arXiv

Decomposing complex tasks into a sequence of simpler subtasks can improve learning efficiency for an autonomous agent. Reinforcement learning (RL) can be used to optimize agent policies to complete subtasks, but requires well-defined subtask rewards and benefits from action masking. Recent work uses large language models (LLMs) to automate reward shaping and action masking, however none of them fully address reactivity to subtask failure and modularity to varying objects for compositional tasks. To overcome these challenges, we develop masking reward behavior tree (MRBT), a symbolic structure used as a reactive and modular reward and action mask function. We design an MRBT template and derive logical specifications to construct and verify MRBTs for a sequence of object-interaction subtasks. Further, we develop an automated pipeline that uses an LLM to generate MRBTs robust to varying task objects, an SMT-solver to verify correctness of specifications, and a neurosymbolic RL loop to train agents on compositional tasks. Experiments demonstrate successful generation and refinement of five MRBTs, consistently improving training efficiency and task success rates over baselines and MRBTs without action masking. We further highlight three advantages of MRBTs: transferability, modularity, and verifiability.