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
Translating natural-language planning intent into verified plans is a longstanding challenge: people communicate goals in language, while classical planners require formal PDDL specifications. Recent agentic frameworks bridge this gap by orchestrating a pool of specialized repair agents inside a verifier-checked refinement loop, but the orchestrator at the centre is itself a prompted frontier LLM, paying a frontier-LLM API call at every refinement step.
arXiv:2605.14483v2 Announce Type: replace
Abstract: Large language models (LLMs) provide a flexible foundation for multi-agent systems, but their effectiveness and computational cost depend criticall...
By Xudong Chen, Yixin Liu, Hua Wei, Kaize Ding
arXiv:2606. 27136v1 Announce Type: new Abstract: For LLM agents in multi-step interactive environments, a key challenge is to make effective use of accumulated interaction experience.
By Shicheng Ye, Chao Yu
The paper introduces Influence-Aware Policy Optimization (IAPO), a method that models multi‑turn agent rollouts as typed influence‑dependency graphs to better assign credit to actions based on how information and errors flow through user and tool interactions. IAPO transforms the structure of support and failure usage into routing weights that redistribute trajectory‑level advantage, enabling more effective learning from sparse final rewards. Experiments with Qwen3‑4B and Qwen3‑8B on three service‑agent benchmarks show that IAPO outperforms existing multi‑turn reinforcement learning baselines without harming function‑calling performance.
By Bo Ren, Yirong Mao, Yi Yang, Wenhui Que
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: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
FL-MAESTRO is a multi‑agent orchestrator that uses three specialized large language model agents to jointly decide the communication topology, per‑client resource allocation, and aggregation rule in each federated learning round. A coordinator merges the agents’ analyses, and a non‑LLM feasibility check validates the decision before execution. By filtering out clients whose updates would never be aggregated, the system eliminates the main source of wasted round energy in volatile edge networks and works across heterogeneous device classes without per‑class energy models, achieving comparable accuracy to the best energy‑aware baseline while reducing wasted energy from over a third to near zero on a non‑IID CIFAR‑10 benchmark.
By Jiajun Wu, Zirui Wang, Jiayu Zhou, Qiang Ye, Steve Drew
AgentOrch is a benchmark that compares global orchestration—where a complete workflow is generated upfront—with step‑by‑step interaction on 650 enterprise standard operating procedures and 3,220 runtime variants. Across all evaluated models, step‑by‑step remains more accurate, but the performance gap has narrowed by about 79% from early to recent models. The study identifies three methods—incremental workflow construction, revising workflows with execution feedback, and targeted training on complete workflows—that can further close the gap, improving global orchestration accuracy by up to 12.18 percentage points.
By Zijie Liu, Qi Yang Huang, Jinhao Duan, Yueh Che Lee, Thomas A. Joseph, Zayne Turner, Adam Seligman, Tianlong Chen, Zhaozhuo Xu
MAS-Loop introduces an execution‑grounded framework that couples an Orchestrator with a trajectory‑conditioned Refiner to close the feedback loop in training‑time multi‑agent system design. For each task, the Orchestrator builds and runs a source MAS, then the Refiner uses the resulting trajectory to locate failures, diagnose them, and propose bounded patches to agents or execution settings. The updated MAS is re‑executed, and the pairwise comparison of outcomes provides learning signals that enable both components to co‑evolve, yielding stronger systems and a new dataset, MAS‑JudgeCorpus, for trajectory‑aware MAS research.
By Hehai Lin, Qi Yang, Chengwei Qin
Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools. In these settings, relevant task information often unfolds over t...
The paper introduces CoPE, a method that trains language agents by adding multi‑step action targets to the policy backbone. By supervising each action forecasted from preceding histories, CoPE enables acting and forecasting to co‑evolve without extra inference cost. Across five benchmarks, CoPE outperforms existing RL baselines, achieving up to twice the sample efficiency on ScienceWorld and improving overall performance on realistic applications.
By Haofei Yu, Yixing Chen, Yining Zhao, Xuyan Ye, Yuxiang Liu, Zhigang Hua, Yan Xie, Shuang Yang, Jiaxuan You