arXiv AI July 22, 2026 By Artem Maryanskyy, Dmitry Budnikov, Alibek T. Kaliyev

When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines

arXiv:2603. 20324v2 Announce Type: replace-cross Abstract: Multi-agent LLM pipelines produce contradictory evidence on whether team diversity improves output quality: heterogeneous Mixture-of-Agents teams outperform single models, yet homogeneous Self-MoA teams consistently win under synthesis-based aggregation.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 2

LLM Consortium for Software Design Refinement: A Controlled Experiment on Multi-Agent Collaboration Topologies

arXiv:2606. 01490v1 Announce Type: cross Abstract: We present a controlled experiment evaluating 12 multi-agent LLM collaboration topologies for software architecture design.

By Nagarjuna Kanamarlapudi, Praveen K

llms agents safety

arXiv AI

Jul 1

ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents

arXiv:2606. 31174v1 Announce Type: new Abstract: Production large language-model (LLM) agents are increasingly deployed not as lone problem-solvers but as managers: a main model creates specialized subagents, delegates work, and orchestrates their parallel, asynchronous returns through dynamic workflows.

By Kaiwen Xiong, Haonian Ji, Shi Qiu, Zeyu Zheng, Cihang Xie, Xinyu Ye, Huaxiu Yao

llms agents multimodal benchmarks

arXiv AI

Aug 11

Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?

arXiv:2608. 09629v1 Announce Type: new Abstract: Self-evolving agents are usually built around prescribed optimization pipelines: the framework decides how to gather evidence, revise a persistent artifact, select candidates, and stop.

By Hui Xue, Fan Yang

llms agents benchmarks

arXiv AI

Aug 10

Does Splitting a Triage Decision Across Agents Hide Bias or Help Catch It? A Multi-Agent Simulation Study of LLM-Based Resource Allocation Under Audit Capacity Constraints

arXiv:2608. 06949v1 Announce Type: new Abstract: Prior benchmarking work has shown that a single large language model (LLM), forced to make life-or-death resource-allocation decisions, exhibits measurable demographic bias.

By Paul-Peter Arslan

llms agents benchmarks safety

arXiv AI

Aug 10

"LLM Agent Performance" Is Not a Single Evaluation Target

arXiv:2602. 03238v3 Announce Type: replace Abstract: LLM agent benchmark scores are shaped not only by the model but also by the agent harness, environment, evaluator, and inference budget.

By Pengyu Zhu, Li Sun, Philip S. Yu, Sen Su

llms agents benchmarks

arXiv AI

Jul 7

MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution

arXiv:2607. 05297v1 Announce Type: new Abstract: Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further extend this capability.

By Zefeng Wang, Minxi Yan, Jinhe Bi, Sikuan Yan, Volker Tresp, Yunpu Ma

llms agents benchmarks

Related stories

LLM Consortium for Software Design Refinement: A Controlled Experiment on Multi-Agent Collaboration Topologies

ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents

Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?

Does Splitting a Triage Decision Across Agents Hide Bias or Help Catch It? A Multi-Agent Simulation Study of LLM-Based Resource Allocation Under Audit Capacity Constraints

"LLM Agent Performance" Is Not a Single Evaluation Target

MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution