Multi-Agent Coding

Follow this topic Ask about this topic

Multi-agent coding studies whether AI systems can solve programming tasks more reliably by dividing work among agents with roles such as planner, coder, tester, and reviewer. Common approaches include dependency-aware task decomposition, adaptive communication topologies, shared workspaces, and feedback from tests, compilers, or runtime tools. Systems are evaluated on settings ranging from competitive-programming benchmarks to repository-level bug fixing and code editing. A central tension is that collaboration can improve correctness and speed, but extra agents also add cost and can introduce conflicts, duplicated work, or errors that pass between agents.

Latest papers

86 papers17 papers in the last four weeks, up 113% on the four weeks before. 0.1% of all new papers.

MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts
Aug 10, 2026Peiwen Li, Shiyang Zhang, Yangtian Zhang +3Multi-Agent LLM Systems Mixture-of-Experts Language Models
Yale University, New Haven, CT, USA
AgentRadio: Passive Awareness for Long-Horizon Multi-Agent Collaboration
Jul 30, 2026Xinxing Ren, Qianbo Zang, Ziyan Wang +4Software Engineering Agents Long-Horizon LLM Agents
1Coral AI Labs · 2SnT, Université du Luxembourg · 3King’s College London +1
An Empirical Study of Coordination Mode as the First-Class Citizen in From-Scratch Multi-Agent Coding
Jul 30, 2026Yanyu Ren, Yunfeng Bai, Xizheng Wang +2Multi-Agent Coordination Multi-Agent Orchestration
1Tsinghua University · 2Zhongguancun Laboratory
Agent Team Work Zone: An Automated, Persistent Workspace for Long-Lived Claude Code Agent Teams
Jul 24, 2026Shouren WangLLM Agent Memory LLM Agent Workflow Optimization
Case Western Reserve University
Cross-Model LLM Code Review: Should you use Claude to review Codex or vice versa?
Jul 22, 2026Zuodong Xiang, Yike Zhang, YueMing Zhang +1Code Generation Evaluation Automated Code Review
University of California, Davis USA · Johns Hopkins University USA · California State University, Long Beach USA
PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents
Jul 21, 2026Tianyue Jiang, Yanlin Wang, Xin He +7LLM Self-Correction Software Engineering Agents
Sun Yat-sen University, China · State Key Laboratory of Blockchain and Data Security, Zhejiang University, China · School of Cyber Science and Engineering, Huazhong University of Science and Technology, China +1
Agents That Teach: Towards Designing Incidental Learning Back into AI-Assisted Software Development
Jul 7, 2026Rohit Mehra, Samdyuti Suri, Prithviraj K Tagadinamani +3Coding Agents Multi-Agent Coding
Accenture Labs, India · Accenture, USA
SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery
Jul 2, 2026Yuvraj Virk, Zack Edds, Chunqiu Steven Xia +1Automated Algorithm Discovery Large Language Model-Guided Optimization
University of Illinois Urbana-Champaign
UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development
Jul 2, 2026Temitayo Olamilekan Ogunsusi, Lijun Qian, Xishuang DongSoftware Engineering Agents Multi-Agent Collaboration
Department of Electrical and Computer Engineering Prairie View A&M University, Prairie View, TX 77446, USA
PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation
Jul 2, 2026Junhao Chen, Xiang Li, Mingjin Chen +9Execution-Guided Code Generation Code Generation
1THU · 2PKU · 3PolyU, Hong Kong +7
ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis
Jun 29, 2026Eagl HuangMulti-Agent Coordination Software Engineering Agents
Eagl Huang
Glite ARF: Verifier-Driven Research with Parallel LLM Coding Agents
Jun 25, 2026Vassili Philippov, Pavel Katunin, Dmitry Andreev +2Multi-Agent Coding Autonomous Research Agents
1Glite · School of Biosciences, The University of Sheffield, Sheffield, UK
CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation
Jun 20, 2026Yifei Wang, Ruiyin Li, Peng Liang +4Repository-Level Code Generation Multi-Agent Coding
School of Computer Science, Wuhan University, China · School of Computer Science, Nanjing University of Science and Technology, China · School of Computer Science, Central China Normal University, China +2
Before the Pull Request: Mining Multi-Agent Coordination
Jun 17, 2026Dipankar SarkarMulti-Agent Coordination Software Engineering Agents
Arizona State University
tap: A File-Based Protocol for Heterogeneous LLM Agent Collaboration
Jun 12, 2026Minseo KimMulti-Agent Communication Multi-LLM Collaboration
HUA Labs, Seoul, Republic of Korea
Recursive Agent Harnesses
Jun 11, 2026Elias Lumer, Sahil Sen, Kevin Paul +1Tool-Augmented Language Model Agents LLM Agent Orchestration
PricewaterhouseCoopers, U.S.
Decentralized Multi-Agent Systems with Shared Context
Jun 9, 2026Yuzhen Mao, Jerry Gu, Aadi Chauhan +3Multi-Agent LLM Systems Multi-Agent System Optimization
Stanford University
When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding
May 31, 2026Xu Yang, Lunyiu Nie, Ethan Chandra +3Graph Partitioning Multi-Agent System Optimization
1The University of Texas at Austin · University of Oxford
How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval
May 29, 2026Nazmus AshrafiSoftware Engineering Code Generation Evaluation
Independent Researcher
The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems
May 27, 2026Nikolay Radev, Lennart Haas, Benjamin Arnav +1AI Agent Security Benchmarks AI Agent Monitoring
Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems
May 27, 2026Seunghyuk Cho, Sunghyun Choi, Jaeseung Heo +4Multi-Agent System Optimization Software Engineering Agents
1Graduate School of Artificial Intelligence, POSTECH · Department of Computer Science and Engineering, POSTECH · 1Graduate School of Artificial Intelligence, POSTECH, 2Department of Computer Science and Engineering, POSTECH
CoRe-Code: Collaborative Reinforcement Learning for Code Generation
May 24, 2026Zhihao Dou, Qinjian Zhao, Zhongwei Wan +2RL for Code Generation Multi-Agent Coordination
Department of Computer Science Kean University · Department of Computer Science Case Western Reserve University
Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game Development
May 22, 2026Srijita Basu, Viktor Kjellberg, Simin Sun +5Multi-Agent Coordination Software Engineering Agents
Chalmers University of Technology and University of Gothenburg · Scania CV AB · Research & Development, Volvo Car Corporation +1
Multi-agent Collaboration with State Management
May 19, 2026Mengyang Liu, Taozhi Chen, Zhenhua Xu +2Multi-Agent Collaboration Multi-Agent Coding
Shanghai Jiaotong University · Cortices AI · Emory University +1
Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
May 14, 2026Han Li, Jinyu Tian, Rili Feng +10RL for Code Generation Continual Learning for LLM Agents
Nanjing University · Independent Researcher · Tsinghua University
ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation
May 13, 2026Zhongkai Yu, Yichen Lin, Chenyang Zhou +12RL for Code Generation Code Generation
UCSD · Columbia University
Evolutionary Ensemble of Agents
May 9, 2026Zongmin Yu, Liu YangAI Agents for Scientific Discovery Evolutionary Optimization
National University of Singapore
MAS-Algorithm: A Workflow for Solving Algorithmic Programming Problems with a Multi-Agent System
May 7, 2026Yuliang Xu, Xiang Xu, Yao Wan +2Competitive Programming Multi-Agent Coding
1Peking University · 2Alibaba Group · 3Huazhong University of Science and Technology
Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation
May 7, 2026Abhijit Talluri, Pujith Anne, Bhagavan Choudary Pendiyala +1Multi-Agent Orchestration Multi-Agent Coding
Independent Researcher
Mise en Place for Agentic Coding: Deliberate Preparation as Context Engineering Methodology
May 6, 2026Andrew ZiglerLLM Planning Agentic Code Generation
LinearB Los Angeles, USA

Aug 10, 2026J/K move · Enter open · S save

MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts

Peiwen Li, Shiyang Zhang, Yangtian Zhang, Sizhuang He+2

Yale University, New Haven, CT, USA

Multi-Agent LLM Systems Mixture-of-Experts Language Models Multi-Agent Orchestration Multi-Agent Coding RL for LLM Agents

Open paper AskPDF arXiv

Large language model-based multi-agent systems have recently shown strong potential for complex, long-horizon tasks. However, existing methods mainly rely on coarse prompt-level differentiation without parameter adaptation for diverse subtasks, resulting in insufficient inter-agent heterogeneity and limited specialized capability that bottleneck performance on tasks with complex requirements. To address this, we introduce a Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts (MoRSE) that distinguishes agents with (role, subtask)-conditional specialization at both the task structure and parameter levels. To make agents' responsibility explicit at the task structure level, we formulate a task-oriented multi-agent system that decomposes each task into a dependency-aware Directed Acyclic Graph of subtasks and assigns each agent a specific (role, subtask), introducing task-level specialization across collaborating agents. Additionally, to address the diverse role and subtask parameter adaptation demands, we propose a dynamic Mixture of (role, subtask) LoRA Experts module with a prototype-based semantic router for subtasks, augmenting agents with parameter-level specialization on a shared LLM substrate cost-effectively. Then, to co-optimize experts and router stably under sparse task rewards, we further propose a hierarchical group-relative policy optimization with two-layer credit assignment that isolates expert updates from the cross-route variance introduced by routing decisions, disentangling expert quality from routing quality. Experiments on code-generation benchmarks across three backbones demonstrate the effectiveness of our approach, with improvements in both whole-task and step-wise performance, and the gains from trained specialization generalize across held-out task categories and domains.