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

arXiv: https://arxiv.org/abs/2506.17784 · HTML: https://mlsanity.com/paper/2506.17784/

## Key facts

- Cited by 25 papers in the map (data through 14 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.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 37)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems](https://mlsanity.com/paper/1705.04146/) (2017)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [Complexity-Based Prompting for Multi-Step Reasoning](https://mlsanity.com/paper/2210.00720/) (2022)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [Scaling Large Language Model-based Multi-Agent Collaboration](https://mlsanity.com/paper/2406.07155/) (2024)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View](https://mlsanity.com/paper/2310.02124/) (2023)
- [Large Language Models for Data Annotation and Synthesis: A Survey](https://mlsanity.com/paper/2402.13446/) (2024)
- [Continuous Deep Q-Learning with Model-based Acceleration](https://mlsanity.com/paper/1603.00748/) (2016)
- [Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization](https://mlsanity.com/paper/2404.02183/) (2024)
- ["Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models](https://mlsanity.com/paper/2406.19417/) (2024)
- [Visual Large Language Models for Generalized and Specialized Applications](https://mlsanity.com/paper/2501.02765/) (2025)
- [Interpreting Pretrained Language Models via Concept Bottlenecks](https://mlsanity.com/paper/2311.05014/) (2023)
- [L2MAC: Large Language Model Automatic Computer for Extensive Code Generation](https://mlsanity.com/paper/2310.02003/) (2023)
- [Knowledge Graph-Enhanced Large Language Models via Path Selection](https://mlsanity.com/paper/2406.13862/) (2024)
- [Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs](https://mlsanity.com/paper/2502.07942/) (2025)
- [Reasoning of Large Language Models over Knowledge Graphs with Super-Relations](https://mlsanity.com/paper/2503.22166/) (2025)

## Built on by (most cited first, 25 of 25)

- [Natural-Language Agent Harnesses](https://mlsanity.com/paper/2603.25723/) (2026)
- [Multi-Agent Debate for LLM Judges with Adaptive Stability Detection](https://mlsanity.com/paper/2510.12697/) (2025)
- [Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects](https://mlsanity.com/paper/2507.21407/) (2025)
- [AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent](https://mlsanity.com/paper/2602.03955/) (2026)
- [SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication](https://mlsanity.com/paper/2508.11733/) (2025)
- [Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models](https://mlsanity.com/paper/2510.07799/) (2025)
- [Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction](https://mlsanity.com/paper/2510.14319/) (2025)
- [Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition](https://mlsanity.com/paper/2604.08708/) (2026)
- [Agentic Services Computing](https://mlsanity.com/paper/2509.24380/) (2025)
- [AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agents](https://mlsanity.com/paper/2603.09716/) (2026)
- [Towards Efficient Agents: A Co-Design of Inference Architecture and System](https://mlsanity.com/paper/2512.18337/) (2025)
- [Learning Latency-Aware Orchestration for Multi-Agent Systems](https://mlsanity.com/paper/2601.10560/) (2026)
- [Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks](https://mlsanity.com/paper/2603.15809/) (2026)
- [TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems](https://mlsanity.com/paper/2601.10120/) (2026)
- [Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems](https://mlsanity.com/paper/2602.11877/) (2026)
- [Learning to Share: Selective Memory for Efficient Parallel Agentic Systems](https://mlsanity.com/paper/2602.05965/) (2026)
- [Taming "Zombie'' Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolution](https://mlsanity.com/paper/2605.17348/) (2026)
- [SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems](https://mlsanity.com/paper/2606.12474/) (2026)
- [Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation](https://mlsanity.com/paper/2511.04700/) (2025)
- [A Multi-Agent Approach to Validate and Refine LLM-Generated Personalized Math Problems](https://mlsanity.com/paper/2604.05160/) (2026)
- [MedRoute: RL-Based Dynamic Specialist Routing in Multi-Agent Medical Diagnosis](https://mlsanity.com/paper/2604.06180/) (2026)
- [From Intent to Execution: Composing Agentic Workflows with Agent Recommendation](https://mlsanity.com/paper/2605.03986/) (2026)
- [Learning Latency-Aware Orchestration for Multi-Agent Systems](https://mlsanity.com/paper/2607.13359/) (2026)
- [CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaboration](https://mlsanity.com/paper/2607.15545/) (2026)
- [Beyond Solo and Consistency: Vindicating Multi-Agent Debate via Conditional Progressive Pruning](https://mlsanity.com/paper/2609.33974/) (2026)

## 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.