UniACE is a unified framework that standardizes the evaluation of large language model (LLM) agents by representing each benchmark as an instruction–tool–environment triplet and running models through a shared, task‑agnostic harness in isolated runtimes. It preserves native success criteria, offers an offline mode for dynamic‑resource tasks, and standardizes efficiency metrics, execution records, and failure attribution. Applying UniACE to 7 benchmarks across 24 domains and 15 models revealed significant score shifts, ranking reversals, and sensitivity to evidence representation, highlighting the impact of evaluation configuration on reported agent performance.
By Pengyu Zhu, Lijun Li, Yaxing Lyu, Qianxin Luo, Jingyi Yang, Yi Liu, Tingfeng Hui, Xinyu Yuan, Li Sun, Sen Su, Jing Shao
arXiv:2606. 01533v1 Announce Type: cross Abstract: Computer use agents (CUAs) today are primarily deployed as single serial agents.
By Jing Yu Koh, Ruslan Salakhutdinov, Daniel Fried
The paper investigates how scaling a team of small language‑model agents affects performance across different orchestration architectures. By testing eight architectures on five short‑answer benchmarks and an executable‑code benchmark, it finds that team scaling yields large gains on arithmetic word‑problem tasks but only modest improvements on multiple‑choice and code generation tasks, with no single architecture dominating all tasks. The authors explain these patterns using a generate‑transform decomposition that separates coverage and transformation effects, showing that arithmetic tasks benefit from both coverage and critic‑guided transformation, while other tasks are limited by saturation or poor conversion.
By Blaz Bertalanic, Carolina Fortuna
arXiv:2606. 00953v1 Announce Type: new Abstract: Multi-agent Large Language Model (LLM) systems offer a way to decompose complex tasks, such as coding, through parallelization and context isolation.
By Xu Yang, Lunyiu Nie, Ethan Chandra, Stanislav Gannutin, Fangru Lin, Swarat Chaudhuri
Agensh is a new multi‑agent harness that eliminates a central orchestrator by letting workers self‑organize through a continuous cooperation loop. The system uses a shared workspace, message interface, and shared context to coordinate tasks, verify results, and merge progress asynchronously. Experiments on ProgramBench and pandoc show that scaling from 1 to 1,024 agents improves test‑pass rates by up to 49% relative, demonstrating that agent count is a viable scaling dimension for complex tasks.
By Zhihao Zhan, Ting Song, Li Dong, Shaohan Huang, Jianxun Lian, Yan Xia, Furu Wei
PeakBench is a new benchmark designed to evaluate how large language model agents invoke multiple tools while respecting resource constraints and parallel execution. It provides executable multi‑tool workflows with dependency annotations and measured resource profiles, and introduces a two‑part evaluation framework that separates logical planning from physical scheduling. The study shows that strong logical planning alone does not guarantee safe or efficient execution, and that providing resource information can reduce overflows and improve utilization.
By Zhi-Kai Chen, Xu-Xiang Zhong, Song-Yan Li, De-Chuan Zhan, Han-Jia Ye
The paper argues that the architecture of multi‑agent large language model (LLM) frameworks, rather than just the intelligence of the underlying models, largely determines system performance. It introduces a taxonomy of architectural dimensions—such as orchestration, memory, planning interfaces, specialization, and communication topology—and presents MAFBench, a unified evaluation suite. An empirical study across nine frameworks, keeping the LLM constant, reveals six design principles and shows that choices like orchestration and communication topology can dramatically affect latency, accuracy, and coordination success.
By Abdelghny Orogat, Ana Rostam, Essam Mansour
arXiv:2606. 01667v1 Announce Type: new Abstract: Test-time scaling has become a major way to improve large language model reasoning, but its orchestration has remained designer-engineered: a fixed sample budget, a fixed refinement loop, a fixed scoring rule, or a fixed search policy decides how compute is spent, leaving the model in charge of solving but not of orchestration.
By Peijia Qin, Qi Cao, Pengtao Xie
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
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: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
arXiv:2603. 21489v2 Announce Type: replace-cross Abstract: AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github.
By Jiayi Geng, Graham Neubig