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.

CorrectRTL: Boost RTL Generation Quality Through Automated Self-Correction with Instruction Decomposition
Oct 18, 2026Jing Wang, Shang Liu, Hangan Zhou +4RTL Code Generation LLM Self-Correction
Hong Kong University of Science and Technology Clear Water Bay, Hong Kong
HTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent Orchestration
Oct 15, 2026Yanchen Deng, Jianguo Huang, Yao Long Teng +6Multi-Agent Orchestration LLM Agent Orchestration
Nanyang Technological University, Singapore · Apodex.
TaReD: Tool-Aware Recursive Decomposition for Long-Horizon Tasks
Oct 8, 2026Wei-Xiang Mao, Zhi-Kai Chen, De-Chuan Zhan +1Tool Discovery for LLM Agents Tool-Using Agents
Nanjing University, China · National Key Laboratory for Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China
Decoupled Multi-Agent Orchestration
Oct 6, 2026Xinle Wu, Yao LuMulti-Agent Orchestration LLM Agent Orchestration
National University of Singapore
Self-Evaluating Recursive Agents
Oct 4, 2026TianYi Lyu, Xiaozhe Li, Yang Li +7LLM Agent Training Recursive Language Models
Tongji University · Independent · Shanghai Artificial Intelligence Laboratory +3
Multi-Granularity Language-Guided Imitation Learning via Instruction Decomposition
Sep 29, 2026Yi-Pei Chiu, Wei-Ta ChuLanguage-Conditioned Robot Manipulation Imitation Learning
National Cheng Kung University, Taiwan
SkillFocus: Evolving Agent Skills via Capability Decomposition
Sep 28, 2026Ning Wang, Zhiren Gong, Bingdong Li +2LLM Agent Skill Learning Task Decomposition
East China Normal University · Nanyang Technological University · Southern University of Science and Technology +1
A Task-Oriented Multi-Agent Framework for Complex Wearable Health Analysis
Sep 21, 2026Kunpeng YangMulti-Agent LLM Systems LLM Agent Orchestration
Renmin University of China
Structured Decomposition for Reliable LLM-Generated Access Control Policies
Sep 21, 2026Vatsal Gupta, Darshan SreenivasamurthyAccess Control LLM Reliability
Apple Inc., Cupertino, CA, USA
What Must Survive? Exact Task-Information--State Frontiers Under Partial Task Revelation
Sep 18, 2026Ronald KatendeInformation-Theoretic Lower Bounds Low-Rank Compression
Decomposition Buys Integrity, Not Yield
Sep 15, 2026Rong HeMulti-Agent System Optimization Deep Research Agents
A Hybrid Dependency-Aware Framework for Task Decomposition and Dynamic Agent Generation in Oracle-to-PostgreSQL Migration
Sep 13, 2026Oleg Grynets, Oleg Kaskun, Alona Seletska +2Code Translation Task Decomposition
EPAM Systems McLean, Virginia, USA · EPAM Systems Lviv, Ukraine · EPAM Systems Kyiv, Ukraine
Conditional Timed Partial Orders: An Expressive and Interpretable Framework for Robot Task Specification and Planning
Sep 7, 2026Sebastian Escobar, Morteza LahijanianRobot Task Planning Task Decomposition
Aerospace Eng. Sci. Dept. at University of Colorado Boulder, CO, USA
Understanding Automatic Mixing: A Subtask-Oriented Analysis of Two-Stage Mixing System
Sep 2, 2026Jinjie Shi, Wei Hua, Kunzhu Xie +3Task Decomposition
Queen Mary University of London, United Kingdom · Guangxi Arts University, China · Wuhan University of Communications, China +2
Does task decomposition improve automatic NLG evaluation?
Sep 1, 2026Sebastian Steindl, Nikos Voskarides, Alberto Gasparin +1LLM Evaluation LLM-as-a-Judge
Amazon, Barcelona, Spain · Amazon, Berlin, Germany
Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweep
Aug 24, 2026Pedro SantosMulti-Agent LLM Systems Task Decomposition
Independent Researcher
Inducing Task Models from Computer-Use Traces
Aug 20, 2026Yucheng Jiang, Zora Zhiruo Wang, Ruishi Chen +1Task Decomposition Process Mining
Stanford University · Carnegie Mellon University
A Two-Tier Perspective on Inference-Time Parallelism in Multi-Agent LLM Systems
Aug 6, 2026Zihan Xu, Haolin Tian, Hai JiangLLM Inference Efficiency Multi-Agent LLM Systems
Beijing University of Posts and Telecommunications.
Project2Task: Graph-Guided Project-Level Planning for Autonomous Research
Aug 5, 2026Huirui Xu, Runtao Xu, Shuo Ren +1AI Agents for Scientific Discovery Graph-Based Planning
Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · School of Future Technology, University of Chinese Academy of Sciences +1
Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer
Aug 4, 2026Janis Zenkner, Tobias Sesterhenn, Tim Grams +1Program Synthesis Task Decomposition
Clausthal University of Technology Clausthal-Zellerfeld, Germany
MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking
Jul 20, 2026HONOR Agentic Search Team, Zhengzong Chen, Lei Tang +27Learning to Rank LLM Planning
HONOR Agentic Search Team
Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval
Jul 7, 2026Yanping Chen, Weijie Shi, Wen Yang +1LLM Planning LLM Reranking
School of Computer Science and Technology, Soochow University · The Hong Kong University of Science and Technology
Task Decomposition for Efficient Annotation
Jun 23, 2026Nupoor Gandhi, Emma StrubellHuman-in-the-Loop Annotation Task Decomposition
Carnegie Mellon University
Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose
Jun 16, 2026Xueping GaoTool-Augmented Language Model Agents LLM Planning
Alibaba Cloud Hangzhou, China
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Jun 8, 2026Pu Ning, Quan Chen, Kun Tao +7Multi-Agent LLM Systems LLM Agent Orchestration
Tsinghua University · Peking University · Ant Group +1
Self-Improving Language Models with Bidirectional Evolutionary Search
May 27, 2026Guowei Xu, Zhenting Qi, Huangyuan Su +4Evolutionary Optimization LLM Planning
Harvard University · MIT
Learning Compositional Symbolic Task Rules from Demonstrations with Inductive Logic Programming
May 26, 2026Oleh Borys, Karla StepanovaRobot Skill Learning Robotic Manipulation
Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague.
Harnesses for Inference-Time Alignment over Execution Trajectories
May 15, 2026Boyuan Wang, Bochao Li, Minghan Wang +2LLM Planning Agent Harness Optimization
Southern University of Science and Technology
Runtime-Structured Task Decomposition for Agentic Coding Systems
May 14, 2026Shubhi Asthana, Bing Zhang, Chad DeLuca +2Software Engineering Agents Agentic Workflows
IBM Research · San Jose, California · Zoom +2
TeamBench: Evaluating Agent Coordination under Enforced Role Separation
May 8, 2026Yubin Kim, Chanwoo Park, Taehan Kim +9Multi-Agent Coordination LLM Agent Evaluation
MIT · Google Research · Independent Researcher +1

Oct 18, 2026J/K move · Enter open · S save

CorrectRTL: Boost RTL Generation Quality Through Automated Self-Correction with Instruction Decomposition

Jing Wang, Shang Liu, Hangan Zhou, Wenji Fang+3

Hong Kong University of Science and Technology Clear Water Bay, Hong Kong

RTL Code Generation LLM Self-Correction Task Decomposition

Open paper AskPDF arXiv

Large language models (LLMs) have shown strong promise in specification-to-RTL generation. Among the explorations, the self-correction paradigm has significantly advanced LLM-based RTL generation. However, two challenges limit further progress. Existing benchmarks are saturated by advanced LLMs, leaving little room to evaluate the agentic self-correction framework. The monolithic self-correction paradigm rewrites the entire design at once, where LLMs are susceptible to error confusion and corruption of originally correct code. To address the benchmark challenge, we contribute ScaleBench, a more challenging benchmark of 200 complex RTL designs. To address the challenge in methodology, we propose CorrectRTL, an agentic framework that realizes a new decompose-then-correct paradigm, in which the LLM agent explicitly decouples scaffold construction from detailed implementation. CorrectRTL contributes three core techniques: (1)Structure-oriented decomposition, (2)Snippet-based RAG, and (3)~SVA-based self-correction. On ScaleBench, CorrectRTL improves Pass@1 from 20.5% to 49.0% (+28.5%). On VerilogEval, CorrectRTL achieves up to 96.1% Pass@1, demonstrating consistent improvements across both simple and complex designs.