mlsanityData to 14 Oct 2026

AdCoEvo: A Co-Evolving Multi-Agent Advertising Delivery System

arXiv 2610.19454 ↗First posted 14 Oct 2026cs.AI cs.IR cs.MAcited by 0

Not on the map. Why?

Abstract (arXiv)

Digital advertising is an important means for platforms to reach potential users and drive business growth. Advertising delivery is the core link between marketing objectives and actual returns. Existing methods have achieved partial automation in individual tasks such as bidding and budget allocation, but they still rely on human operators for overall coordination, making it difficult to support large-scale operations. They also often fail to achieve optimal performance, and individual experience remains difficult to turn into reusable operational capabilities. In addition, as advertising markets change, advertising delivery systems need timely strategy updates to remain effective in dynamic markets. To automate the entire advertising operations process and improve adaptability to market changes, we propose AdCoEvo, a co-evolving multi-agent advertising delivery system. Specifically, the system connects delivery decisions across different timescales and operational granularities through role specialization. Diagnostic results guide account planning and strategy adjustment in the next period. The multi-agent system updates its model parameters based on actual delivery outcomes and continually improves delivery strategies through mutual feedback among planning, adjustment, and diagnosis, thereby achieving co-evolution. Experiments show that, relative to the rule-based operational baseline (Rule), AdCoEvo increases advertiser value by 14.02% while reducing cost per acquisition by 7.07%. Compared with a multi-agent system with fixed parameters, AdCoEvo increases advertiser value by 3.96% and reduces cost per acquisition by 1.24%, indicating that co-evolution can yield greater delivery returns.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 14 Oct 2026.

Builds on

32 of 42 references.

References · 32

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  5. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  6. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  7. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  8. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  9. 2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 1,040
  10. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  11. 2025Group Sequence Policy Optimizationcited by 835
  12. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
20 more
  1. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 392
  2. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 338
  3. 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 256
  4. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolutioncited by 134
  5. 2025Multi-Agent Design: Optimizing Agents with Better Prompts and Topologiescited by 113
  6. 2017Real-Time Bidding by Reinforcement Learning in Display Advertisingcited by 91
  7. 2024MALT: Improving Reasoning with Multi-Agent LLM Trainingcited by 76
  8. 2025In-the-Flow Agentic System Optimization for Effective Planning and Tool Usecited by 72
  9. 2018Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertisingcited by 61
  10. 2026Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learningcited by 37
  11. 2025Flow: Modularized Agentic Workflow Automationcited by 34
  12. 2022Sustainable Online Reinforcement Learning for Auto-biddingcited by 29
  13. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 29
  14. 2024AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Gamescited by 28
  15. 2025Generalizable End-to-End Tool-Use RL with Synthetic CodeGymcited by 17
  16. 2025RTBAgent: A LLM-based Agent System for Real-Time Biddingcited by 14
  17. 2025Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systemscited by 12
  18. 2026DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMscited by 4
  19. 2020Real-Time Optimisation for Online Learning in Auctionscited by 3
  20. 2026Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes?cited by 1

Built on by

Not cited yet.