paper-with-me

Papers

Heddle: A Distributed Orchestration System for Agentic RL Rollout

2026-03-30 · Zili Zhang, Yinmin Zhong, Chengxu Yang, Chao Jin, Bingyang Wu, Xinming Wei, Yuliang Liu, Xin Jin arxiv

Agentic Reinforcement Learning (RL) enables LLMs to solve complex tasks by alternating between a data-collection rollout phase and a policy training phase. During rollout, the agent generates trajectories, i.e., multi-step interactions between LLMs and external tools. Yet, frequent tool calls induce long-tailed trajectory generation that bottlenecks rollouts. This stems from step-centric designs that ignore trajectory context, triggering three system problems for long-tail trajectory generation: queueing delays, interference overhead, and inflated per-token time. We propose Heddle, a trajectory-centric system to optimize the when, where, and how of agentic rollout execution. Heddle integrates three core mechanisms: trajectory-level scheduling using runtime prediction and progressive priority to minimize cumulative queueing; trajectory-aware placement via presorted dynamic programming and opportunistic migration during idle tool call intervals to minimize interference; and trajectory-adaptive resource manager that dynamically tunes model parallelism to accelerate the per-token time of long-tail trajectories while maintaining high throughput for short trajectories. Evaluations across diverse agentic RL workloads demonstrate that Heddle effectively neutralizes the long-tail bottleneck, achieving up to 2.5$\times$ higher end-to-end rollout throughput compared to state-of-the-art baselines.

📄 PDF Abstract BibTeX arXiv:2603.28101

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents

2026-03-19 · Hao Zhang, Mingjie Liu, Shaokun Zhang, Songyang Han 외 arxiv

Multi-turn LLM agents are increasingly important for solving complex, interactive tasks, and reinforcement learning (RL) is a key ingredient for improving their long-horizon behavior. However, RL training requires genera…

Reinforcement Learning

Internet of Agentic Things: Networked AI Agents for Closed-Loop IoT Orchestration

2026-07-14 · Quanyan Zhu arxiv

The paper introduces the Internet of Agentic Things (IoAT), an architectural framework that integrates agentic AI, IoT, cyber-physical systems, Physical AI, edge computing, and digital twins into a unified closed-loop or…

Decision Making

Agentic Federated Learning: The Future of Distributed Training Orchestration

2026-04-06 · Rafael O. Jarczewski, Gabriel U. Talasso, Leandro Villas, Allan M. de Souza arxiv

Although Federated Learning (FL) promises privacy and distributed collaboration, its effectiveness in real-world scenarios is often hampered by the stochastic heterogeneity of clients and unpredictable system dynamics. E…

Federated Learning

Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception

2026-04-19 · Ashutosh Bajpai, Tamal Majumder, Akshay Nambi, Tanmoy Chakraborty arxiv

Small Vision-Language Models (SVLMs) are efficient task controllers but often suffer from visual brittleness and poor tool orchestration. They typically require expensive supervised trajectory tuning to mitigate these de…

Reinforcement Learning

MTTR-A: Measuring Cognitive Recovery Latency in Multi-Agent Systems

2025-11-08 · Barak Or arxiv

Reliability in multi-agent systems (MAS) built on large language models is increasingly limited by cognitive failures rather than infrastructure faults. Existing observability tools describe failures but do not quantify …