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.

Evolving Agent Teams
Oct 27, 2026Shiyi Cao, Ziming Mao, Dacheng Li +2Multi-Agent Coding Self-Evolving Agents
University of California, Berkeley
CodeMeepo: A Multi-Agent Workflow for Repository-Level Code Migration and Optimization
Oct 25, 2026Farzad Habibi, Changrong Wu, Jinzhou Jiang +1Code Translation Multi-Agent Coding
University of California, Irvine · Microsoft · OpenAI
MulFCoder: Framework-conditioned Multi-agent for MLLM-based Multi-framework Front-end Code Generation
Oct 25, 2026Jie Wu, Haoran Ma, Shisong Tang +3Code Generation Image-to-Code Generation
Communication University of China · Harvard University · Tsinghua university +3
Policy Search in Code Space for Multi-Agent Pathfinding
Oct 19, 2026Matthias Eder, Pantelis Emmanouil, Vivek Farias +7Multi-Agent Path Finding Program Synthesis
KNAPP · MIT · Columbia University +1
3DCodeVerse: Exploring 3D Worlds as Code
Oct 15, 2026Yipeng Gao, Ziyao Zeng, Jinfa Huang +16Agentic Code Generation 3D Asset Generation
University of Southern California · Yale University · University of Rochester +6
A team of Gemini 4 Argon agents beats Minecraft
Oct 15, 2026Maxence Faldor, Satinder Singh, Roberta RaileanuGame-Playing Agents Agentic Code Generation
Google DeepMind
SCARCE: Emergent Institutions in Long-Horizon Multi-Agent Coding Systems
Oct 15, 2026Abhinav Kumar, Rediet Abebe, Eugene Bagdasarian +1Multi-Agent Resource Allocation Multi-Agent Systems
University of Massachusetts Amherst · ELLIS Institute Tübingen · MPI for Intelligent Systems +1
Origin Attribution for Unsafe Behavior in Self-Evolving Multi-Agent Coding Systems
Oct 12, 2026Hanyi Yu, Jiaming CuiAI Agent Security Multi-Agent Coding
University of Southern California, Los Angeles, CA · Virginia Tech, Blacksburg, VA
Scaling Inference-Time Compute with Teams of Coding Agents
Oct 12, 2026Keenan Samway, Daniel D'souza, Omar Darwiche Domingues +3Inference-Time Scaling Inference-Time Compute Allocation
Cohere Labs · Cohere
Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems
Oct 9, 2026Yuepeng Hu, Pegah Ghahremani, Reza Aghajani +2Reward Hacking Multi-Agent Systems
Meta Superintelligence Labs · Duke University
Humanize: Judgement Engineering for Agentic Coding
Oct 6, 2026Sihao Liu, Ligeng Zhu, Zijian Zhang +6Multi-Agent Coding LLM Agent Orchestration
NVIDIA · UCLA · Tsinghua University +2
Verifying Coordination in Parallel Coding Agents: NP-Bench and a Scheduling Planner
Oct 5, 2026Sumanyu MukuCoding Agent Benchmarks Multi-Agent Coordination
Amira Learning
MemMux: Runtime Verification and Honest Resource Attribution for Fleets of Parallel Coding Agents
Oct 5, 2026Sumanyu MukuRuntime Enforcement for AI Agents AI Agent Monitoring
Amira Learning
AECP: Artifact-Exclusive Communication Protocol for Multi-Agent Code Generation
Oct 5, 2026Jiaqi Xue, Yanjun Wang, Xiangci Li +5Multi-Agent Coordination Multi-Agent Communication
University of Central Florida · AWS AI Labs
CodeForge-MA: Execution-Verified Multi-Agent Learning with Language-Conditioned LoRA for Multilingual Code Generation
Oct 4, 2026Zhizhou Gu, Xianting Wu, Siyu Gu +2RL for Code Generation Synthetic Data Generation for Language Models
Northeastern University Bellevue, USA · Columbia University New York, USA · University of Pennsylvania Philadelphia, USA +2
RankEvolve: A Reliable Multi-Agent Auto-Research Harness for Evolving Ranking Models
Sep 30, 2026Zheng Chen, Linfeng Liu, Hong Li +1Learning to Rank LLM Agent Orchestration
Meta
OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
Sep 29, 2026Chun-Wah Hsu, Kai Gong, Yu Wu +12Multi-Agent Orchestration Multi-Agent Collaboration
Shanghai Jiao Tong University · University of Cambridge · Nanyang Technological University +4
RAVEN: Receiver-Conditioned Action-Value Encoding for Finite-Alphabet Multi-Agent Communication
Sep 29, 2026Shuwei Sun, Chenxi Wang, Jian Huang +2Rate-Distortion Optimization Multi-Agent Communication
Xi’an Jiaotong University Xi’an, China
ParallelPilot: Supporting Coordination and Monitoring in Parallel AI Coding
Sep 27, 2026Tao Long, Weili Shi, Hussein Mozannar +2AI Agent Monitoring Human Oversight of AI
Microsoft Research AI Frontiers, Columbia University, USA · Microsoft Research AI Frontiers, USA
AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering
Sep 26, 2026Kaituo Zhang, Zhen Xiong, Zhimeng Jiang +8Multi-Agent Collaboration Multi-Agent Coding
University of Houston · New York University · Texas A&M University +3
Agensh: Scaling Organizational Intelligence to 1,024 Agents
Sep 22, 2026Zhihao Zhan, Ting Song, Li Dong +4Multi-Agent Coordination Multi-Agent Orchestration
Microsoft Research
Passes Alone, Fails Together: Benchmarking Semantic Coordination in Parallel LLM-Agent Development
Sep 21, 2026Haocheng Xia, Eugene Wu, Yongjoo ParkLLM Agent Evaluation AI Agent Benchmarks
University of Illinois Urbana-Champaign Champaign, USA · Columbia University New York, USA
LearnActCoder: Role-Aware Error Memory for Adaptive Clinical Coding Agents
Sep 17, 2026Meysam Ghaffari, Bhaskar Sen, Nasim Sabetpour +3Adaptive Inference Automated Medical Coding
Optum AI · Harvard University
Learning How Much to Collaborate: Difficulty-Aware Topology Selection for Multi-Agent Code Generation
Sep 12, 2026Yunsong HongMulti-Agent Coding Agentic Code Generation
School of Computer Science, The University of Sydney, Sydney, NSW 2006, Australia
How AI Coders Discuss, Disagree, and Reach Consensus: Challenges and Opportunities for LLM-Based Qualitative Coding
Sep 10, 2026Jeongyeon Kim, John MitchellMulti-Agent LLM Systems LLM Agent Evaluation
Stanford University, Stanford, CA, USA
MaxKernel: Agentic Kernel Generation for TPUs
Sep 3, 2026Shangkun Wang, Nina Cai, Charles Hoong +7Large Language Model-Guided Optimization Multi-Agent Coding
1Google · 2Google DeepMind
MARS: Multi-Specialist LLM Relay System for Competitive Programming
Aug 24, 2026Andrei Mikhailov, Mikhail Burtsev, Alsu SagirovaLLM-Based Program Synthesis Multi-Agent Coding
MIRAI · London Institute for Mathematical Sciences · AXXX
AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
Aug 24, 2026Seonglae Cho, Donghyun LeeMulti-Agent Coding Multi-Agent Coordination
Holistic AI · University of California, Berkeley
When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding
Aug 17, 2026Giuseppe Destefanis, Tomaso AsteMulti-Agent Coordination Multi-Agent Coding
Department of Computer Science, University College London, UK
Adversarial Review: Structured Disagreement for Grounded Agentic Code Review
Aug 16, 2026Eric S. Qiu, Joyce GillAutomated Code Review Multi-Agent Coding
Cornell University · Stanford University

Oct 27, 2026J/K move · Enter open · S save

Evolving Agent Teams

Shiyi Cao, Ziming Mao, Dacheng Li, Joseph E. Gonzalez+1

University of California, Berkeley

Multi-Agent Coding Self-Evolving Agents LLM Agent Workflow Optimization GPU Kernel Optimization

Open paper AskPDF arXiv

The rapid progress of software engineering agents drives interest in applying them to open-ended problems such as GPU kernel optimization. However, we find that existing coding agents converge to local optima on real-world, expert-written kernels (e.g., FlashInfer). We introduce Evolving Agent Teams, a multi-agent framework that escapes such local optima. It features (1) a central supervisor that diagnoses each local optimum and restructures a team of agents; and (2) a persistent file system that comprises a learning document, an evolution history, and per-team artifacts, grounding restructuring with accumulated experience. Under a matched token budget, Evolving Agent Teams consistently outperforms strong coding-agent baselines. With an extended token budget, Evolving Agent Teams generates a CUDA kernel that reaches 1.2x mean speedup over the production FlashInfer MLA paged decode kernel from scratch and wins on 36 of 47 production workloads from FlashInfer-Bench (0.86-0.99x on the remaining 11). It also demonstrates superior performance on tasks such as KDA prefill on AMD MI350X (3.01x over vLLM) and NVIDIA B200 (3.44x over FlashKDA), MoE expert-offload serving on Apple silicon (30.3 tokens/s decode for Qwen3.8-Flash-Next in MLX 4-bit on a 48 GB M4 Pro), and RoboDojo robot manipulation (62.1 on held-out seeds vs. 55.3 for the best leaderboard entry). Code is available at https://github.com/caoshiyi/EAT.