The paper introduces NP‑Bench, a benchmark and a proactive scheduling planner that coordinates parallel large‑language‑model coding agents. By partitioning work scopes and ordering merges ahead of time, the planner improves clean‑integration rates from 1/9 to 9/9 and eliminates merge conflicts, outperforming both no‑coordination and reactive‑detection baselines. It also demonstrates that cross‑session memory can eliminate repeated mistakes and that routing facts to agents does not improve long‑context accuracy at scale.
By Sumanyu Muku
arXiv:2610.28286v1 Announce Type: cross
Abstract: Teams of large language model (LLM) agents are increasingly applied to complex tasks, but their collaboration protocols are mostly designed empirical...
By Ivan Ilin, Peter Richt\'arik
arXiv:2608. 07532v1 Announce Type: new Abstract: Modern agentic AI systems combine multiple large language model agents with heterogeneous skills, yet most architectures either fix communication in advance or allow full broadcast.
By Mojtaba Eslami
arXiv:2609.39559v1 Announce Type: new
Abstract: In this work we study the problem of MAPFC, a post-optimization step for Multi-Agent Path Finding (MAPF) plans where we are given a feasible plan produ...
By Oren Salzman
arXiv:2607.01767v3 Announce Type: replace
Abstract: Long-horizon language agents make interdependent decisions across multiple rounds, forming growing planning graphs in which later decisions depend...
By Xinyuan Song, Zekun Cai
arXiv:2608. 09366v1 Announce Type: new Abstract: Large-scale learning systems often face the challenge of balancing multiple, potentially competing objectives, such as fairness, accuracy, and latency.
By Corinna Cortes, Yishay Mansour, Mehryar Mohri
Decentralized Multi-Agent Coordination and Communication in Shared Codebases introduces ParallACT, a benchmark for studying how coding agents with independent, human‑driven requests interact in shared repositories. The benchmark includes complementary tasks that require agents to cooperate via a shared interface, and contradictory tasks where agents’ edits conflict, leading to poor merged outcomes. Experiments show that a single‑agent oracle outperforms parallel agents, especially on contradictory tasks, and that merely notifying agents of each other or providing a communication channel only marginally improves performance at a token cost.
By Rishabh Mediratta, Lingyun Xiao, Peter Stone, Joydeep Biswas, Elias Stengel-Eskin
CollabFlow introduces a recursive self‑improvement framework for multi‑agent collaboration in large language model systems. It trains a Collab‑Director to assemble teams of agents, uses a frozen executor to run them, and retrains the director each round based on outcomes. The system incorporates evidence‑conditioned communication protocols within collaboration graphs and a Collaborative Trajectory Balance objective to maintain diverse high‑performing teams across rounds, achieving superior performance on twelve datasets.
By Xiao Huang, Mingda Zhang, Junming Zhang, Qiang Huang, Hanwen Zhang, Yue Dai, Zijia Wang, Xiaoying Tang
arXiv:2609.07204v1 Announce Type: new
Abstract: The minimum cut problem for an undirected edge-weighted graph asks us to divide its set of nodes into two blocks while minimizing the weighted sum of t...
By David A. Bader, Adil Chhabra, Ernestine Gro{\ss}mann, Monika Henzinger, Alexander Noe, Christian Schulz
arXiv:2611.05916v1 Announce Type: cross
Abstract: We study the minimum-disagreement cluster editing problem that, from a complete edge-signed graph, where a positive edge represents two vertices agre...
By Cong Ma, Guangting Chen, Yong Chen, Guohui Lin, Jiaxuan Ma, Lusheng Wang
The paper introduces InFlowOp, a label‑free optimization framework that assigns costs to each decision in a multi‑agent workflow, balancing agent competence against execution time. It determines task granularity and agent assignment before execution and corrects faults during execution using the same cost metric. The authors also present Braid, a benchmark for multi‑agent coordination, and show that InFlowOp outperforms single‑agent baselines by up to 11.97% across various domains.
By Xuehang Guo, Haoyu Wang, Shengyu Chen, Zach Chen, Wei Cheng, Qingyun Wang, Haifeng Chen
arXiv:2610.41129v1 Announce Type: new
Abstract: AI agents increasingly carry out delegated tasks in parallel, with one person overseeing several of them at once. In practice, an agent often lacks inf...
By Hanzhao Wang, Shengjie Liu, Zhengchao Wang