arXiv AI August 7, 2026 By Zihan Xu, Haolin Tian, Hai Jiang

A Two-Tier Perspective on Inference-Time Parallelism in Multi-Agent LLM Systems

arXiv:2608. 05791v1 Announce Type: cross Abstract: Large language model (LLM)-driven multi-agent systems typically require multiple model invocations and complex coordination during inference, and their execution strategies directly affect system accuracy, latency, and computational cost.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 12

The Illusion of Multi-Agent Advantage

arXiv:2606. 13003v1 Announce Type: new Abstract: Prevailing wisdom posits that Multi-Agent Systems (MAS) are superior to Single-Agent Systems (SAS), citing advantages like context protection, parallel processing and distributed decision-making.

By Prathyusha Jwalapuram, Hehai Lin, Chuyuan Li, Fangkai Jiao, Sudong Wang, Yifei Ming, Zixuan Ke, Chengwei Qin, Giuseppe Carenini, Shafiq Joty

agents benchmarks

arXiv AI

Jun 16

Learning to Share: Selective Memory for Efficient Parallel Agentic Systems

arXiv:2602. 05965v2 Announce Type: replace-cross Abstract: Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results.

By Joseph Fioresi, Parth Parag Kulkarni, Ashmal Vayani, Song Wang, Mubarak Shah

agents reinforcement-learning benchmarks

arXiv AI

Jul 8

Decision Protocols in Multi-Agent Large Language Model Conversations

arXiv:2607. 05477v1 Announce Type: cross Abstract: Improving the task performance of Large Language Models (LLMs) is essential, yet scaling these models faces significant challenges such as diminishing returns and high costs.

By Lars Benedikt Kaesberg

llms agents benchmarks

arXiv AI

Jul 24

InferenceBench: A Benchmark for Open-Ended LLM Inference Optimization by AI Agents

arXiv:2607. 20468v1 Announce Type: new Abstract: AI agents are increasingly used to automate research and development tasks, yet existing benchmarks typically evaluate them on prescribed workflows or narrow action spaces.

By Jehyeok Yeon, Ben Rank, Maksym Andriushchenko

llms agents efficiency benchmarks

arXiv AI

Aug 26

Parason: Revealing Subtask and Trial Parallelism in LLM Reasoning

Parason is a new framework that discovers and exploits both subtask and trial parallelism in large language model (LLM) reasoning. By converting sequential reasoning traces into structured parallel trajectories and training with Parallelism-Aware Group Relative Policy Optimization, it balances accuracy, latency, and parallelism. Experiments on mathematical reasoning benchmarks such as AIME24 and AIME25 show that Parason achieves an average acceleration of about 1.7× while maintaining competitive accuracy.

By Zhengyang Zhang, Zijian Zhang, Jiaxuan Gao, Shusheng Xu, Yi Wu, Song Han, Ligeng Zhu

llms benchmarks

arXiv AI

Aug 14

Learning Latency-Aware Orchestration for Multi-Agent Systems

arXiv:2601. 10560v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) coordinate multiple LLM-powered agents through structured workflows, gaining reasoning power but incurring high inference latency from multi-step execution and repeated model invocations.

By Xi Shi, Mengxin Zheng, Qian Lou

llms agents efficiency benchmarks

One email a morning, machine-written

Related stories

The Illusion of Multi-Agent Advantage

Learning to Share: Selective Memory for Efficient Parallel Agentic Systems

Decision Protocols in Multi-Agent Large Language Model Conversations

InferenceBench: A Benchmark for Open-Ended LLM Inference Optimization by AI Agents

Parason: Revealing Subtask and Trial Parallelism in LLM Reasoning

Learning Latency-Aware Orchestration for Multi-Agent Systems