The paper introduces POrchestra, a proactive agentic orchestration framework that lets sub‑agents request harness adjustments during execution, enhancing adaptability to dynamic environments. It also proposes On‑Policy Orchestration Distillation (OPOD), which uses hindsight feedback from sub‑agents’ requests to provide targeted improvement signals for training the orchestration policy. Experiments on three long‑horizon benchmarks show that POrchestra boosts task success by about 9.1% over the best baseline, and with OPOD the improvement rises to 10.0%, while also improving cost‑performance trade‑offs.
By Xueyang Feng, Chaozhuo Li, Xiaohe Bo, Jiakai Tang, Chenxi Li, Qiwei Ye, Xu Chen
SwarmBench is a new benchmark designed to evaluate large language models (LLMs) as orchestrators of agent swarms, assessing accuracy, efficiency, cost, and process quality. The study finds significant variations in orchestration performance among current models, affecting not only final outcomes but also the quality of the orchestration process itself. To address these gaps, the authors introduce SwarmExp, a method that uses experience extraction and replay to consistently enhance LLM orchestration performance.
By Jinshan Gao, Zhuoran Jin, Tianyi Men, Kang Liu, Jun Zhao
Build and launch cloud agents with the Agents API, a managed service powered by the Codex harness for orchestration, long-running sessions, and tool use.
A technical deep dive into the Codex agent loop, explaining how Codex CLI orchestrates models, tools, prompts, and performance using the Responses API.
The paper investigates challenges in open‑source large‑language‑model (LLM) based multi‑agent systems (MAS). By analyzing 944 issues extracted from 21 projects, it finds that orchestration and execution problems are most common, with workflow, tool integration, and memory issues as primary causes. The predominant remedy identified is optimizing workflow, and the study offers empirically grounded implications for improving orchestration, tool integration, and memory mechanisms in LLM‑based MAS.
By Asad Ur Rehman, Syed Mohammad Kashif, Ruiyin Li, Peng Liang, Zengyang Li, Arif Ali Khan
arXiv:2606. 01351v1 Announce Type: new Abstract: The transition from single-turn models to Multi-Agent Systems (MAS) promises enhanced problem-solving capabilities, yet the centralized orchestration topology remains a critical point of fragility.
By Junze Zhu, Weihao Chen, Xuanwang Zhang, Zhen Wu, Xinyu Dai
arXiv:2606. 31518v1 Announce Type: new Abstract: Agentic Business Process Management has gained momentum recently.
By Stefanie Rinderle-Ma, Juergen Mangler, Johannes Loebbecke, Dominik Voigt, Nataliia Klievtsova, Matthias Ehrendorfer
BuildBench introduces a realistic benchmark for evaluating large language model agents on the task of compiling open‑source software (OSS). It includes diverse OSS projects that lack clear build instructions, have undocumented dependencies, and may require source patching or script modification. The authors also present OSS‑BUILD‑AGENT, a baseline LLM‑based agent that retrieves build instructions effectively and achieves state‑of‑the‑art performance on the benchmark.
By Zehua Zhang, Ati Priya Bajaj, Divij Handa, Siyu Liu, Arvind S Raj, Hongkai Chen, Hulin Wang, Yibo Liu, Zion Leonahenahe Basque, Souradip Nath, Vishal Juneja, Nikhil Chapre, Tiffany Bao, Yan Shoshitaishvili, Adam Doup\'e, Chitta Baral, Ruoyu Wang
arXiv:2610.07556v1 Announce Type: new
Abstract: Learned orchestration can automatically construct effective language-model multi-agent systems, but existing approaches couple planning to fixed worker...
By Xinle Wu, Yao Lu
arXiv:2608. 05263v1 Announce Type: new Abstract: Multi-agent orchestration frameworks are moving from demos to production, yet benchmarks typically report task accuracy without diagnosing why a pipeline failed, where a cascade began, or which routing decision caused the breakdown.
By Yidian Chen, Yingzi Gu, Natan Vidra, Spurthi Setty, Sharon Zheng
Learn how Jason Liu uses Codex to preserve context, manage complex projects, and help work continue beyond a single prompt.
arXiv:2607. 02873v1 Announce Type: cross Abstract: Large language model agents driving security tool suites over the Model Context Protocol are increasingly common.
By Romain Gerard, Assmaa Zeghaider, Yan Guo