Astraea: A State-Aware Scheduling Engine for LLM-Powered Agents

• URL: http://arxiv.org/abs/2512.14142v1
• Date: Tue, 16 Dec 2025 06:55:10 GMT
• Title: Astraea: A State-Aware Scheduling Engine for LLM-Powered Agents
• Authors: Hongqiu Ni, Jiabao Zhang, Guopeng Li, Zilong Wang, Ruiqi Wu, Chi Zhang, Haisheng Tan,
• Abstract summary: Astraea is a service engine designed to shift the optimization from local segments to the global request lifecycle.<n>It employs a state-aware, hierarchical scheduling algorithm that integrates a request's historical state with future predictions.<n>Astraea reduces average JCT by up to 25.5% compared to baseline methods.
• Score: 12.884297990127985
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) are increasingly being deployed as intelligent agents. Their multi-stage workflows, which alternate between local computation and calls to external network services like Web APIs, introduce a mismatch in their execution pattern and the scheduling granularity of existing inference systems such as vLLM. Existing systems typically focus on per-segment optimization which prevents them from minimizing the end-to-end latency of the complete agentic workflow, i.e., the global Job Completion Time (JCT) over the entire request lifecycle. To address this limitation, we propose Astraea, a service engine designed to shift the optimization from local segments to the global request lifecycle. Astraea employs a state-aware, hierarchical scheduling algorithm that integrates a request's historical state with future predictions. It dynamically classifies requests by their I/O and compute intensive nature and uses an enhanced HRRN policy to balance efficiency and fairness. Astraea also implements an adaptive KV cache manager that intelligently handles the agent state during I/O waits based on the system memory pressure. Extensive experiments show that Astraea reduces average JCT by up to 25.5\% compared to baseline methods. Moreover, our approach demonstrates strong robustness and stability under high load across various model scales.

Related papers

• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• Asynchronous MultiAgent Reinforcement Learning for 5G Routing under Side Constraints [1.0732935873226022]
  We propose an asynchronous multi-agent reinforcement learning framework in which independent PPO agents plan routes in parallel and commit resource deltas to a shared global resource environment.<n>We evaluate the method on an O-RAN like network simulation using nearly real-time traffic data from the city of Montreal.<n>AMARL achieves a similar Grade of Service (GoS) and end-to-end latency, with reduced training wall-clock time and improved robustness to demand shifts.
  arXiv  Detail & Related papers  (2026-01-18T18:38:37Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• Deep Q-Learning-Based Intelligent Scheduling for ETL Optimization in Heterogeneous Data Environments [10.31577390735368]
  This paper proposes an intelligent scheduling optimization framework based on deep Q-learning.<n>The framework formalizes the scheduling process as a Markov Decision Process.<n>It enables adaptive decision-making by a reinforcement learning agent in high-dimensional state spaces.
  arXiv  Detail & Related papers  (2025-12-15T07:38:47Z)
• xLLM Technical Report [57.13120905321185]
  We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework.<n>xLLM builds a novel decoupled service-engine architecture.<n>xLLM-Engine co-optimizes system and algorithm designs to fully saturate computing resources.
  arXiv  Detail & Related papers  (2025-10-16T13:53:47Z)
• Slim Scheduler: A Runtime-Aware RL and Scheduler System for Efficient CNN Inference [0.0]
  Slim Scheduler integrates a Proximal Policy Optimization (PPO) reinforcement learning policy with algorithmic, greedy schedulers to coordinate distributed inference for slimmable models.<n>This hierarchical design reduces search space complexity, mitigates overfitting to specific hardware, and balances efficiency and throughput.
  arXiv  Detail & Related papers  (2025-10-10T05:44:05Z)
• CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems [62.24576366776727]
  We propose a latency-aware scheduling framework to minimize total inference latency.<n>We show that the proposed method significantly reduces cold-start latency compared to baseline strategies.
  arXiv  Detail & Related papers  (2025-08-15T07:49:22Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal [55.13854171147104]
  Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development.<n>We present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents.<n>We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2.
  arXiv  Detail & Related papers  (2025-03-18T14:02:59Z)
• A Bayesian Framework of Deep Reinforcement Learning for Joint O-RAN/MEC Orchestration [12.914011030970814]
  Multi-access Edge Computing (MEC) can be implemented together with Open Radio Access Network (O-RAN) over commodity platforms to offer low-cost deployment. In this paper, a joint O-RAN/MEC orchestration using a Bayesian deep reinforcement learning (RL)-based framework is proposed.
  arXiv  Detail & Related papers  (2023-12-26T18:04:49Z)
• A Deep Recurrent-Reinforcement Learning Method for Intelligent AutoScaling of Serverless Functions [18.36339203254509]
  F introduces a lightweight, function-based cloud execution model that finds its relevance in a range of applications like IoT-edge data processing and anomaly detection.
  arXiv  Detail & Related papers  (2023-08-11T04:41:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.