arXiv AI

FL-MAESTRO: Multi-Agent LLM Orchestration for Resource-Constrained Federated Learning

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.

arXiv Computation and Language

Oct 12

Proactive Agentic Orchestration

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

llms agents efficiency 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

arXiv AI

Jun 11

INFRAMIND: Infrastructure-Aware Multi-Agent Orchestration

arXiv:2606. 11440v1 Announce Type: new Abstract: Existing multi-agent LLM orchestration methods, ranging from brute-force ensembles to learned routers, select models and topologies based on task and model features.

By Ahasan Kabir, Jiaqi Xue, Mengxin Zheng, Qian Lou

llms agents reinforcement-learning benchmarks

Hugging Face Trending Papers

Jun 19

Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents

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.

llms agents fine-tuning benchmarks

arXiv Machine Learning

Sep 30

Agentic Federated Learning: Rule-Based Client and Server Agents for Adaptive Training

arXiv:2609.35914v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it suitable for privacy-sens...

By Deepthy K. Bhaskar, VP Binu, B Minimol

agents benchmarks safety

arXiv AI

Oct 1

HO-FL: Hybrid-Order Federated Learning for Heterogeneous Edge Devices

arXiv:2609.39074v1 Announce Type: cross Abstract: Federated learning (FL) on memory-constrained edge devices faces a dilemma: first-order (FO) optimization (i.e., backpropagation) demands substantial...

By Qiyuan Chen, Xian Wu, Yanan Ma, Xianhao Chen

safety

arXiv AI

Jun 10

Decentralized Multi-Agent Systems with Shared Context

arXiv:2606. 10662v1 Announce Type: cross Abstract: Multi-agent systems (MAS) can scale large language model reasoning at test time by decomposing complex problems into parallel subtasks.

By Yuzhen Mao, Azalia Mirhoseini

llms agents

arXiv AI

Jun 3

Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments

arXiv:2606. 03892v1 Announce Type: cross Abstract: Training LLMs to orchestrate multi-step tool calls is held back by three coupled obstacles: realistic stateful execution environments are costly to build, synthetic training queries are often detached from the server's actual state (so the generated tool calls fail to execute), and recall-based RL rewards incentivize verbose tool-calling patterns.

By Ibrahim Abdelaziz, Asim Munawar, Kinjal Basu, Maxwell Crouse, Chulaka Gunasekara, Suneet Katrekar, Pavan Kapanipathi

llms agents reinforcement-learning

arXiv Machine Learning

Oct 7

Tram-FL: Reducing Communication and Computation Costs through Sequential Model Circulation in Decentralized Federated Learning

arXiv:2610.07859v1 Announce Type: new Abstract: Conventional decentralized federated learning (DFL) often focuses on clients, with each client maintaining a model copy, performing updates individuall...

By Kota Maejima, Takayuki Nishio, Asato Yamazaki, Yuko Hara-Azumi

efficiency

arXiv AI

Sep 10

AgentServeSim: Serving-System Simulation and Policy Search for LLM Agent Programs

AgentServeSim is a simulation framework designed to model the execution of large language model (LLM) agent programs, capturing cross‑turn key‑value (KV) state retention, successor turn release, and scheduling decisions. Unlike existing simulators that operate on request streams, AgentServeSim treats the entire agent program as a single unit of execution, using a Program Control Block, Program Orchestrator, Retention Plane, and Dispatch Plane to emulate realistic serving dynamics. Validation against real vLLM deployments on two GPU platforms shows mean job completion time errors below 5.5%, and the simulator enables automated policy search that improves mean JCT by up to 2.8% over hand‑written policies. whyItMatters":"The simulator provides a realistic, CPU‑based tool for evaluating and optimizing LLM agent serving policies, achieving high fidelity to real deployments and enabling measurable performance gains."

By Rakibul Hasan Rajib, Mengxin Zheng, Qian Lou

llms agents

arXiv Machine Learning

Jul 9

Robust Federated Learning Under Real-World Client Churn

arXiv:2607. 06979v1 Announce Type: new Abstract: Federated Learning (FL) enables training shared models on private, on-device data, but production deployments remain constrained to slow, multi-day refresh cycles due to the complexity of coordinating massive client populations.

By Dhruv Garg, Neha Lakhani, Debopam Sanyal, Myungjin Lee, Alexey Tumanov, Ada Gavrilovska

agents benchmarks

arXiv AI

Sep 30

COLLATOR: Compositional Multi-Agent Orchestration with Counterfactual Reinforcement Learning

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

llms agents reinforcement-learning benchmarks

Related stories