The study examines how swapping members in large‑language‑model (LLM) teams affects performance. By replacing a team member with a newcomer who either carries the original team’s written notebook, a notebook from another team, or no notebook, the authors find that newcomers with the original notebook often outperform those without it in cooperative tasks such as cooking, wildfire response, and medical Q&A. However, when compared to the original team, these replacements consistently underperform and require more messages per unit of progress, with the deficit persisting across model families and decoding temperatures and narrowing only when planning‑only members are added.
By Jianxin Gao, Runze Li, Tianyi Yu, Liangwei Ren, Bohan Chen, Zining Wang
The paper investigates how coordination among AI agents serving different users degrades performance compared to a single coordinating agent. Across five advanced models and 77 scenarios in four shared-resource environments—API key budgets, clinic calendars, personal assistant bookings, and merge queues—the study finds that multi‑agent teams consistently underperform, sometimes collapsing entirely, and that even with communication channels coordination overhead remains significant. The authors identify specific failure modes such as stalling, action overriding, and claim fabrication, and propose environment‑specific mitigations like team leads and procedural instructions, while releasing the MAMUBench benchmark for future research.
By Sahan Paliskara, Nattaput Namchittai, Andrew Lampinen
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:2607. 25446v1 Announce Type: new Abstract: Multi-agent frameworks built on large language models (LLMs) routinely entangle three logically distinct concerns: who is on the team (organization), how members align (coordination), and which algorithm fuses their work (collaboration protocol).
By Huan Chen, Xiang Song, Jian Jin, Pan Ren, Liang-Jie Zhang
arXiv:2605. 15207v2 Announce Type: replace Abstract: Multi-agent LLM systems have shown promise for complex reasoning, yet recent evaluations reveal they often underperform single-model baselines.
By Yi Xie, Siao Liu, Falong Fan, Yuanqi Yao, Yue Zhao, Bo Liu
arXiv:2608.23541v1 Announce Type: cross
Abstract: Does multi-agent LLM interaction help or hurt? Some work reports gains from debate (Du et al., 2024), critique loops (Chen et al., 2025), and mixture...
By Summer Eunhyung Ann, Haokun Liu, Chenhao Tan
arXiv:2608. 16801v1 Announce Type: new Abstract: We study how teams of AI coding agents coordinate while solving programming tasks.
By Giuseppe Destefanis, Tomaso Aste
The study evaluates whether multi‑agent systems (MAS) outperform single‑agent systems (SAS) when agents interact with users under a written policy on the dual‑control benchmark. Across 7,950 simulated conversations in airline, retail, and telecom domains, the MAS performed worse in 12 of 13 valid cells and tied only once, with a negative average gain of 28 points. Even in scenarios where prior theory predicted a benefit, the MAS lost performance and incurred higher token costs.
By Ethan Yang, Xiangcheng Shi
The paper introduces Steiner’s taxonomy of group tasks to study how multi‑agent large language model (LLM) teams scale on disjunctive versus compensatory tasks. By modeling agents as conditionally independent given the item, it shows that plurality voting converges to the modal answer while averaging converges to the item‑level bias. Experiments with 13 open‑weight models and up to 30 agents reveal that disjunctive tasks benefit from larger teams, whereas compensatory tasks like Fermi estimation see little improvement, highlighting that task structure and aggregation method fundamentally determine team scaling.
By Carolina Fortuna, Blaz Bertalanic
arXiv:2608. 08239v1 Announce Type: new Abstract: LLM routers promise efficiency by matching each request to the cheapest adequate model, and are increasingly applied per step inside multi-step agents.
By Ashritha Gonuguntla
arXiv:2610.33201v1 Announce Type: cross
Abstract: LLM agents take instructions from the operator, repository configuration, user, tool results and saved memory, which often conflict. Instruction-hier...
By Anish Laddha, Nitesh Pradhan, Gaurav Srivastava
arXiv:2606. 19111v1 Announce Type: cross Abstract: Team science holds that leadership is contingent: it helps only under specific conditions, and capable, autonomous teams may need none at all.
By Haewoon Kwak