MAFP applies fictitious play to LLM multi-agent systems to resolve stance entanglement in competitive decision-making, outperforming single-round and multi-round baselines on tournament strength and robustness.
hub Canonical reference
Multi-Agent Collaboration Mechanisms: A Survey of LLMs
Canonical reference. 100% of citing Pith papers cite this work as background.
85
Pith papers citing it
16
external citations · Pith
Background
100% of classified citations
abstract
With recent advances in Large Language Models (LLMs), Agentic AI has become phenomenal in real-world applications, moving toward multiple LLM-based agents to perceive, learn, reason, and act collaboratively. These LLM-based Multi-Agent Systems (MASs) enable groups of intelligent agents to coordinate and solve complex tasks collectively at scale, transitioning from isolated models to collaboration-centric approaches. This work provides an extensive survey of the collaborative aspect of MASs and introduces an extensible framework to guide future research. Our framework characterizes collaboration mechanisms based on key dimensions: actors (agents involved), types (e.g., cooperation, competition, or coopetition), structures (e.g., peer-to-peer, centralized, or distributed), strategies (e.g., role-based or model-based), and coordination protocols. Through a review of existing methodologies, our findings serve as a foundation for demystifying and advancing LLM-based MASs toward more intelligent and collaborative solutions for complex, real-world use cases. In addition, various applications of MASs across diverse domains, including 5G/6G networks, Industry 5.0, question answering, and social and cultural settings, are also investigated, demonstrating their wider adoption and broader impacts. Finally, we identify key lessons learned, open challenges, and potential research directions of MASs towards artificial collective intelligence.
hub tools
citation-role summary
background 19
citation-polarity summary
roles
background 18polarities
background 18representative citing papers
Heterogeneous agents achieve dense latent KV-cache communication via lightweight cross-model transformation and two-phase training, outperforming text at lower compute in context-aware settings and enabling context-unaware transfer.
EinsteinArena is a platform for AI agents to collectively discover new mathematical results through open interaction, achieving 12 new state-of-the-art outcomes including raising the 11-dimensional kissing number lower bound from 593 to 604.
CollabSim is a new CSCW-grounded simulation framework that enables controlled multi-agent experiments to measure collaborative competence in LLM agents.
Soap2Soap uses a multi-agent system with dual-bridge consistency via JSON screenplays and visual anchors plus batch keyframe generation to achieve better long-term consistency in cinematic video remaking than commercial APIs.
A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.
HAM³ achieves up to 78.3% attack success rate on the GQA benchmark by hierarchically attacking perception, communication, and reasoning layers in multi-modal multi-agent systems.
TADI shows that domain-specialized tools orchestrated by an LLM over dual structured and semantic databases can convert heterogeneous wellsite data into evidence-grounded drilling intelligence, with tool design mattering more than model scale.
OMC framework turns multi-agent AI into self-organizing companies with Talents, Talent Market, and E²R search, achieving 84.67% success on PRDBench (15.48 points above prior art).
GraphBit is a DAG-based engine-orchestrated framework for agentic LLMs that achieves 67.6% accuracy with zero hallucinations on GAIA benchmarks.
M³KG-RAG improves multimodal reasoning in large language models by constructing multi-hop knowledge graphs and selectively pruning retrieved context with GRASP.
Anonymization in multi-agent debate reduces identity bias by equalizing self and peer weights in a Bayesian update model, quantified by the Identity Bias Coefficient.
A systematic audit of LLM-based AI societies finds that 89.7% of 39 studies violate at least one of six PIMMUR validity principles, with reproductions showing that many claimed collective behaviors disappear when controls are tightened.
HQRE entropy regularization makes multi-agent LLM coordination well-posed, yielding unique equilibria, linear mirror convergence, bounded Bayesian regret, and DICE gains of 4.3–8.5 pp on reasoning/planning tasks.
A benchmark for LLM agents in partially observable joint decision-making reveals that deliberation challenges current models but can enable reflection and error correction.
Persistent decision history plus role-separated redacted evaluation lets agents continually improve skills across sessions and outperform commercial deep-research and prior skill-evolution baselines.
Multicultural multi-agent LLM systems exhibit substantially lower value diversity than human societies on the World Values Survey, with diversity uncorrelated to per-agent alignment and further reduced by agent interactions.
MOC formalizes a multi-order evidence stream and Semantic-Topological Merging algorithm that improves task performance while cutting communication costs on six datasets.
TRACER combines a controller-regret layer using regret matching for speak/skip decisions with a generation-credit layer using GSPO rewards to enable learned collaboration in multi-LLM reasoning.
Decentralized AI agent teams self-organize around hypotheses, critique proposals, and share knowledge to outperform single-agent baselines on biomedical ML, language-model optimization, and protein fitness tasks.
MACReD is a multi-agent collaborative reasoning framework for reaction diagram parsing that reports state-of-the-art F1 scores of 75.2% and 84.6% on the RxnScribe benchmark.
Formalizes design space for human-LLM collaborative planning along mode, scope, and level axes; evaluates AMBIPOM prototype via user study and benchmark revealing hybrid workflows and trade-offs.
LCGuard applies adversarial training to transform KV cache artifacts in multi-agent LLMs, reducing reconstructable sensitive information while preserving task performance.
AgentCo-op retrieves and assembles existing agents and tools into interoperable workflows for open-world scientific tasks, showing effectiveness in genomics case studies and competitive benchmark results with lower costs.
citing papers explorer
-
Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play
MAFP applies fictitious play to LLM multi-agent systems to resolve stance entanglement in competitive decision-making, outperforming single-round and multi-round baselines on tournament strength and robustness.
-
See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents
Heterogeneous agents achieve dense latent KV-cache communication via lightweight cross-model transformation and two-phase training, outperforming text at lower compute in context-aware settings and enabling context-unaware transfer.
-
Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries
EinsteinArena is a platform for AI agents to collectively discover new mathematical results through open interaction, achieving 12 new state-of-the-art outcomes including raising the 11-dimensional kissing number lower bound from 593 to 604.
-
CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments
CollabSim is a new CSCW-grounded simulation framework that enables controlled multi-agent experiments to measure collaborative competence in LLM agents.
-
Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration
Soap2Soap uses a multi-agent system with dual-bridge consistency via JSON screenplays and visual anchors plus batch keyframe generation to achieve better long-term consistency in cinematic video remaking than commercial APIs.
-
Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.
-
Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning
HAM³ achieves up to 78.3% attack success rate on the GQA benchmark by hierarchically attacking perception, communication, and reasoning layers in multi-modal multi-agent systems.
-
TADI: Tool-Augmented Drilling Intelligence via Agentic LLM Orchestration over Heterogeneous Wellsite Data
TADI shows that domain-specialized tools orchestrated by an LLM over dual structured and semantic databases can convert heterogeneous wellsite data into evidence-grounded drilling intelligence, with tool design mattering more than model scale.
-
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
OMC framework turns multi-agent AI into self-organizing companies with Talents, Talent Market, and E²R search, achieving 84.67% success on PRDBench (15.48 points above prior art).
-
GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration
GraphBit is a DAG-based engine-orchestrated framework for agentic LLMs that achieves 67.6% accuracy with zero hallucinations on GAIA benchmarks.
-
M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation
M³KG-RAG improves multimodal reasoning in large language models by constructing multi-hop knowledge graphs and selectively pruning retrieved context with GRASP.
-
When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning
Anonymization in multi-agent debate reduces identity bias by equalizing self and peer weights in a Bayesian update model, quantified by the Identity Bias Coefficient.
-
The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies
A systematic audit of LLM-based AI societies finds that 89.7% of 39 studies violate at least one of six PIMMUR validity principles, with reproductions showing that many claimed collective behaviors disappear when controls are tightened.
-
DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination
HQRE entropy regularization makes multi-agent LLM coordination well-posed, yielding unique equilibria, linear mirror convergence, bounded Bayesian regret, and DICE gains of 4.3–8.5 pp on reasoning/planning tasks.
-
LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability
A benchmark for LLM agents in partially observable joint decision-making reveals that deliberation challenges current models but can enable reflection and error correction.
-
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History
Persistent decision history plus role-separated redacted evaluation lets agents continually improve skills across sessions and outperform commercial deep-research and prior skill-evolution baselines.
-
Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems
Multicultural multi-agent LLM systems exhibit substantially lower value diversity than human societies on the World Values Survey, with diversity uncorrelated to per-agent alignment and further reduced by agent interactions.
-
MOC: Multi-Order Communication in LLM-based Multi-Agent Systems
MOC formalizes a multi-order evidence stream and Semantic-Topological Merging algorithm that improves task performance while cutting communication costs on six datasets.
-
TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning
TRACER combines a controller-regret layer using regret matching for speak/skip decisions with a generation-credit layer using GSPO rewards to enable learned collaboration in multi-LLM reasoning.
-
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Decentralized AI agent teams self-organize around hypotheses, critique proposals, and share knowledge to outperform single-agent baselines on biomedical ML, language-model optimization, and protein fitness tasks.
-
MACReD: A Multi-Agent Collaborative Reasoning Framework for Reaction Diagram Parsing
MACReD is a multi-agent collaborative reasoning framework for reaction diagram parsing that reports state-of-the-art F1 scores of 75.2% and 84.6% on the RxnScribe benchmark.
-
How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning
Formalizes design space for human-LLM collaborative planning along mode, scope, and level axes; evaluates AMBIPOM prototype via user study and benchmark revealing hybrid workflows and trade-offs.
-
LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
LCGuard applies adversarial training to transform KV cache artifacts in multi-agent LLMs, reducing reconstructable sensitive information while preserving task performance.
-
AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows
AgentCo-op retrieves and assembles existing agents and tools into interoperable workflows for open-world scientific tasks, showing effectiveness in genomics case studies and competitive benchmark results with lower costs.
-
Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling
SIGMA builds a signed relational graph among LLM agents and uses conflict-aware message passing plus weighted aggregation to produce more consistent predictions than prior cooperative-assumption baselines.
-
CHAL: Council of Hierarchical Agentic Language
CHAL is a multi-agent dialectic system that performs structured belief optimization over defeasible domains using Bayesian-inspired graph representations and configurable meta-cognitive value system hyperparameters.
-
Rollout Cards: A Reproducibility Standard for Agent Research
Rollout cards preserve complete agent rollout records and declare the reporting rules behind scores, enabling reproducible evaluation where changing only the rule can alter success rates by over 20 percentage points.
-
Conformity Generates Collective Misalignment in AI Agents Societies
Populations of individually aligned AI agents reach stable misaligned states through conformity, with small adversarial agents able to trigger irreversible tipping points.
-
STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning
STAR presents a failure-aware routing framework using a state-conditioned transition policy and an agent routing matrix combining expert routes with learned recoveries from execution traces to improve multi-agent spatiotemporal reasoning.
-
A Versatile AI Agent for Rare Disease Diagnosis and Risk Gene Prioritization
Hygieia is a new AI agent system that integrates phenotypes, genetics, and records to achieve superior rare disease diagnosis and gene prioritization with confidence scores.
-
Self-Adaptive Multi-Agent LLM-Based Security Pattern Selection for IoT Systems
ASPO combines multi-agent LLM proposals with deterministic enforcement in a MAPE-K loop to select conflict-free, resource-feasible security patterns for IoT, delivering 100% safety invariants and 21-23% tail latency/energy reductions on testbed workloads.
-
Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization
TPGO represents multi-agent systems as graphs of textual parameters and applies group relative optimization to enable self-improvement from execution history.
-
Explicit Trait Inference for Multi-Agent Coordination
ETI lets LLM agents infer and track partners' psychological traits (warmth and competence) from histories, cutting payoff loss 45-77% in games and boosting performance 3-29% on MultiAgentBench versus CoT baselines.
-
AgentGate: A Lightweight Structured Routing Engine for the Internet of Agents
AgentGate decomposes routing into action decision and structural grounding stages, allowing small 3B-7B models to dispatch queries competitively on a curated benchmark after targeted fine-tuning.
-
Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems
LLM agent societies develop power-law coordination cascades and intellectual elites through an integration bottleneck that grows with system size.
-
Agentic Business Process Management: A Research Manifesto
Agentic Business Process Management reframes BPM around autonomous agents that must exhibit framed autonomy, explainability, conversational actionability, and self-modification to keep their actions aligned with organizational objectives.
-
Security Considerations for Multi-agent Systems
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
-
Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning
Prompt-R1 is an end-to-end RL framework where a small-scale LLM collaborates with large-scale LLMs by generating prompts, using a dual-constrained reward to optimize correctness and quality, and outperforms baselines on public datasets.
-
PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation
PosterForest uses a hierarchical Poster Tree and content-layout agent collaboration to generate scientific posters from papers without training, outperforming prior automated methods in human and automated evaluation.
-
BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
BlindGuard introduces an unsupervised hierarchical agent encoder plus corruption-guided contrastive detector that identifies malicious agents in LLM-based multi-agent systems without any attack labels or prior knowledge of malicious behaviors.
-
GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
-
NaviAgent: Bilevel Planning on Tool Navigation Graph for Large-Scale Orchestration
NaviAgent decouples task planning from tool execution via a Tool World Navigation Model graph to improve scalability and success rates in LLM agents handling large tool ecosystems.
-
To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
Introduces six-dimension trustworthiness definition and attention-based A-Trust score with a TMS to improve LLM-MAS robustness against malicious or unreliable messages.
-
Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search
DITS replaces Q-value guidance in MCTS with influence scores for synthetic data synthesis in multi-agent LLM training, claiming better efficiency and performance on eight datasets.
-
Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration
Clarus is a four-layer collaboration infrastructure with a project-agent-resource model that reformulates research as an open, traceable, multi-participant process.
-
Multi-Agent Transactive Memory
MATM is a retrieval framework that lets populations of LLM agents share and reuse task trajectories to improve performance on interactive tasks without joint training.
-
A Technical Taxonomy of LLM Agent Communication Protocols
Creates a five-dimension taxonomy (counterparty, payload, interaction state, discovery mechanism, schema flexibility) from nine protocols and identifies architectural patterns plus convergence trends.
-
CAF-Gen: A Multi-Agent System for Enriching Argumentation Structures
CAF-Gen uses an iterative multi-agent creator-reviewer process to enrich shallow argument mining outputs into structurally richer CAF-compliant models with claimed improvements over single-pass generation.
-
Exploring the Topology and Memory of Consensus: How LLM Agents Agree, Fragment, or Settle When Forming Conventions
Simulations of 16 LLM agents in a naming game on 8 topologies show memory depth interacts with network structure to flip coordination speed and increase fragmentation in centralized networks.
-
APE: Agentic Prompt Enhancer for Image Generation and Editing
APE post-trains small language models as single-agent or multi-agent prompt enhancers that improve visual alignment on image generation and editing benchmarks without altering the downstream visual model.