mlsanityData to 14 Oct 2026

Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing

arXiv 2608.12371 ↗First posted 19 Jul 2026cs.AIcited by 0

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Stream-processing systems increasingly operate across heterogeneous mobile edge--cloud infrastructures, where workload volatility, resource contention, and stringent quality-of-service (QoS) requirements complicate decentralized scheduling. This paper proposes MAS-DecStream, whose main contribution is LLM-MR-CNP: an extension of the classical Contract Net Protocol with semantic CFP formulation, progressive context disclosure, multi-round proposal revision, negotiation memory, and deterministic validation. Edge-cluster agents refine natural-language offloading proposals from local observations, predicted resource states, and qualitative runtime context, while hard resource and QoS constraints remain deterministic. Experiments derived from the Alibaba ASI Trace evaluate the extension at three levels: single- versus multi-round CNP, rule-based versus LLM-assisted refinement, and fixed-model single- versus multi-round negotiation. Under the evaluated configurations, MAS-DecStream reduces latency violations to 3%, eliminates resource overcommitment, reaches a conflict-resolution rate of 0.91 with 20 agents, and improves utility by up to 22% over the multi-round rule-based baseline. A separate 25-case evaluation shows model- and prompt-dependent accuracy--cost trade-offs. The results provide initial evidence that multi-round CNP refinement is the principal protocol-level gain, with LLM assistance adding value for qualitative and uncertain runtime context.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 20 of its 32 references that are in the map. First posted on arXiv 19 Jul 2026.

Builds on

20 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation16 Aug

Other references · 19

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  3. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  4. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  5. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  6. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 241
  7. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 169
  8. 2024Improving Multi-Agent Debate with Sparse Communication Topologycited by 107
  9. 2019Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networkscited by 79
  10. 2024MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoningcited by 41
  11. 2024Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selectioncited by 33
  12. 2026Solver-Aided Verification of Policy Compliance in Tool-Augmented LLM Agentscited by 16
7 more
  1. 2025CoLMDriver: LLM-based Negotiation Benefits Cooperative Autonomous Drivingcited by 13
  2. 2025Blueprint First, Model Second: A Framework for Deterministic LLM Workflowcited by 12
  3. 2024Large Language Models for Power Scheduling: A User-Centric Approachcited by 8
  4. 2023Deep Reinforcement Learning-based Scheduling for Optimizing System Load and Response Time in Edge and Fog Computing Environmentscited by 6
  5. 2026TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systemscited by 2
  6. 2026Multi-Turn Reasoning LLMs for Task Offloading in Mobile Edge Computingcited by 1
  7. 2026An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026When Do LLM Agents Help? Deadline-Aware Mixed-Criticality Task Scheduling at the Autonomous-Vehicle Edge
  2. 2026Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs
  3. 2026SARA: SLO-Aware Resource Allocation for Disaggregated Agentic LLM Services
  4. 2026End-to-End Latency-Minimizing and Load-Balanced Request Scheduling for Edge LLM Inference in Agentic AI Services
  5. 2026HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling
  6. 2026CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Cloud-Edge Systems
  7. 2026Multi-Agentic AI for Fairness-Aware and Accelerated Multi-modal Large Model Inference in Real-world Mobile Edge Networks
  8. 2026DEALS: Decentralized Expertise-Aware Load Serving for Multi-Agent LLM Systems