mlsanityData to 7 Oct 2026

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction

arXiv 2506.17784 ↗First posted 21 Jun 2025cs.AIcited by 25

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Recent progress in large language model (LLM)-based multi-agent collaboration highlights the power of structured communication in enabling collective intelligence. However, existing methods largely rely on static or graph-based inter-agent topologies, lacking the potential adaptability and flexibility in communication. In this work, we propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure, offering a significantly larger topology space for multi-agent communication. Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection (NCS), which enables each agent to selectively access relevant information from any previous step. Together, these components construct task-adaptive communication pipelines that support both role flexibility and global information flow. Extensive evaluations across multiple benchmarks demonstrate that our approach achieves superior performance while substantially reducing communication overhead.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 37 of its 51 references that are in the map. First posted on arXiv 21 Jun 2025.

Builds on

37 of 51 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Thoughts without Thinking: Reconsidering the Explanatory Value of Chain-of-Thought Reasoning in LLMs through Agentic Pipelines1 May
  2. 2024Scaling Large Language Model-based Multi-Agent Collaboration11 Jun

Other references · 35

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  8. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  9. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  10. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  11. 2025s1: Simple test-time scalingcited by 1,311
  12. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
23 more
  1. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  2. 2025LIMO: Less is More for Reasoningcited by 488
  3. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 387
  4. 2022CodeT: Code Generation with Generated Testscited by 369
  5. 2016Solving General Arithmetic Word Problemscited by 353
  6. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  7. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  8. 2024Large Language Models for Data Annotation and Synthesis: A Surveycited by 201
  9. 2016Continuous Deep Q-Learning with Model-based Accelerationcited by 149
  10. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimizationcited by 84
  11. 2024"Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Modelscited by 60
  12. 2025Visual Large Language Models for Generalized and Specialized Applicationscited by 35
  13. 2023Interpreting Pretrained Language Models via Concept Bottleneckscited by 33
  14. 2023L2MAC: Large Language Model Automatic Computer for Extensive Code Generationcited by 30
  15. 2024Knowledge Graph-Enhanced Large Language Models via Path Selectioncited by 28
  16. 2025Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMscited by 24
  17. 2025Reasoning of Large Language Models over Knowledge Graphs with Super-Relationscited by 21
  18. 2024Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity gamescited by 20
  19. 2025MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learningcited by 13
  20. 2024Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approachcited by 11
  21. 2024Understanding Reasoning in Chain-of-Thought from the Hopfieldian Viewcited by 10
  22. 2024FastGAS: Fast Graph-based Annotation Selection for In-Context Learningcited by 8
  23. 2025Efficient MAP Estimation of LLM Judgment Performance with Prior Transfercited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 17.

25 papers.

Sort:

By area:

  1. 2026Natural-Language Agent Harnessescited by 54
  2. 2025Multi-Agent Debate for LLM Judges with Adaptive Stability Detectioncited by 20
  3. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectscited by 14
  4. 2025SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communicationcited by 12
  5. 2026AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agentcited by 12
  6. 2025Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Modelscited by 11
  7. 2025Agentic Services Computingcited by 6
  8. 2025Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstructioncited by 6
  9. 2026AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agentscited by 5
  10. 2026Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decompositioncited by 5
  11. 2025Towards Efficient Agents: A Co-Design of Inference Architecture and Systemcited by 4
  12. 2026TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systemscited by 3
13 more
  1. 2026Learning Latency-Aware Orchestration for Multi-Agent Systemscited by 3
  2. 2026Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networkscited by 3
  3. 2026Learning to Share: Selective Memory for Efficient Parallel Agentic Systemscited by 2
  4. 2026Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systemscited by 2
  5. 2026Taming "Zombie'' Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolutioncited by 1
  6. 2026SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systemscited by 1
  7. 2025Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generationcited by 0
  8. 2026A Multi-Agent Approach to Validate and Refine LLM-Generated Personalized Math Problemscited by 0
  9. 2026MedRoute: RL-Based Dynamic Specialist Routing in Multi-Agent Medical Diagnosiscited by 0
  10. 2026From Intent to Execution: Composing Agentic Workflows with Agent Recommendationcited by 0
  11. 2026Learning Latency-Aware Orchestration for Multi-Agent Systemscited by 0
  12. 2026CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaborationcited by 0
  13. 2026Beyond Solo and Consistency: Vindicating Multi-Agent Debate via Conditional Progressive Pruningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Adaptive Graph Pruning for Multi-Agent Communication
  2. 2026Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems
  3. 2026Rethinking Multi-Agent Collaboration: When More Is Less
  4. 2026GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
  5. 2025Stochastic Self-Organization in Multi-Agent Systems
  6. 2025Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems
  7. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
  8. 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems