Pith. sign in

REVIEW 18 cited by

A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.17481 v2 pith:PC4DACBT submitted 2024-12-23 cs.CL cs.MA

Shuaihang Chen , Yuanxing Liu , Wei Han , Weinan Zhang , Ting Liu This is my paper
classification cs.CLcs.MA
keywords llm-masllm-basedmulti-agentpreviousresearchstudiessurveyadvances
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

LLM-based Multi-Agent Systems ( LLM-MAS ) have become a research hotspot since the rise of large language models (LLMs). However, with the continuous influx of new related works, the existing reviews struggle to capture them comprehensively. This paper presents a comprehensive survey of these studies. We first discuss the definition of LLM-MAS, a framework encompassing much of previous work. We provide an overview of the various applications of LLM-MAS in (i) solving complex tasks, (ii) simulating specific scenarios, and (iii) evaluating generative agents. Building on previous studies, we also highlight several challenges and propose future directions for research in this field.

Discussion (0). Sign in to comment.

Forward citations

Cited by 18 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles

    cs.AI 2026-05 unverdicted novelty 7.0 of 10

    ScioMind combines anchoring-based belief updates, hierarchical memory, and dynamic profiles in LLM multi-agent systems to produce more stable, diverse, and psychologically aligned opinion trajectories than prior fixed...

  2. Asking Questions the Right Way: A Multi-Agent Conversational System for Prompt Formulation in Complex Task Resolution

    cs.MA 2026-08 conditional novelty 6.0 of 10

    An eight-agent question-asking system that front-loads intent clarification produced more complete prompts, higher-rated outputs, and single-turn task completion in a four-person pilot, with unstable effect sizes.

  3. Agentic Re-Casting using Agentic Re-Simulations

    hep-ph 2026-07 conditional novelty 6.0 of 10

    An agentic AI system with a physicist in the loop re-casts an ATLAS ttZ measurement into a global top-quark SMEFT fit and recovers injected coloron Wilson coefficients in a repeatable benchmark.

  4. When Do Multi-Agent Systems Help? An Information Bottleneck Perspective

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Multi-agent LLM systems help exactly when the context removed by compressed relays outweighs the downstream-relevant information those relays discard.

  5. MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    A new benchmark study finds that prompt optimization can deliver significant gains in multi-agent LLM systems but its effectiveness varies strongly with task, workflow, communication protocol, and team size.

  6. MOC: Multi-Order Communication in LLM-based Multi-Agent Systems

    cs.AI 2026-06 unverdicted novelty 6.0 of 10

    MOC formalizes a multi-order evidence stream and Semantic-Topological Merging algorithm that improves task performance while cutting communication costs on six datasets.

  7. ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems

    cs.MA 2026-02 conditional novelty 6.0 of 10

    A perturbation-based framework measures how value opinions propagate through multi-agent LLM systems, revealing that susceptibility varies by value, model, and topology.

  8. MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryMetabolomics Knowledge Graphs

    cs.AI 2025-10 conditional novelty 6.0 of 10

    A multi-agent LLM system converts natural-language metabolomics questions into SPARQL queries over the ENPKG knowledge graph, reaching 83.67% accuracy with GPT-4o versus 8.16% for the standalone model.

  9. Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration

    cs.AI 2026-06 unverdicted novelty 5.0 of 10

    Clarus is a four-layer collaboration infrastructure with a project-agent-resource model that reformulates research as an open, traceable, multi-participant process.

  10. Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?

    cs.MA 2026-05 unverdicted novelty 5.0 of 10

    Multi-agent LLM deliberation is modeled as input-dependent Friedkin-Johnsen dynamics equivalent to a mixture of experts, with influence analyzed via confidence and alignment proxies.

  11. Agent Manufacturing: Foundation-Model Agents as First-Class Industrial Entities

    cs.AI 2026-05 unverdicted novelty 5.0 of 10

    Agent Manufacturing is defined as manufacturing systems whose principal coordination uses foundation-model agents for open-ended goal interpretation, long-horizon planning, tool invocation, and negotiation.

  12. Multi-Agentic Approach for History Matching of Oil Reservoirs

    cs.MA 2026-05 unverdicted novelty 5.0 of 10

    PetroGraph is a multi-agent LLM system that automates reservoir history matching and reduces mismatch by 95% on SPE1, 69% on SPE9, and 13% on the Norne field model.

  13. Chinese Short-Form Creative Content Generation via Explanation-Oriented Multi-Objective Optimization

    cs.CL 2025-11 unverdicted novelty 5.0 of 10

    MAGIC-HMO is a multi-agent framework that treats Chinese short-form creative NLG as heterogeneous multi-objective optimization over personalized constraints plus explanation reliability and outperforms baselines on a ...

  14. Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future Directions

    cs.CR 2026-08 conditional novelty 4.0 of 10

    A survey proposing a five-dimensional taxonomy of trust crises in open AI agent networks and analyzing blockchain's role as a shared trust infrastructure.

  15. Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces

    cs.CL 2026-05 unverdicted novelty 4.0 of 10

    This survey organizes RL for LLM multi-agent systems into reward families, credit units, and five orchestration sub-decisions, notes the absence of explicit stopping-decision training in its paper pool, and releases a...

  16. Toward Human-Centered Multi-Agent Systems: Integrating Cognition, Culture, Values, and Cooperation in AI Agents

    cs.MA 2026-06 conditional novelty 3.0 of 10

    A survey arguing that multi-agent AI systems remain task-centric and lack integrated computational models of human cognition, culture, values, and social cooperation.

  17. Toward Human-Centered Multi-Agent Systems: Integrating Cognition, Culture, Values, and Cooperation in AI Agents

    cs.MA 2026-06 unverdicted novelty 3.0 of 10

    A literature survey across cognitive science, sociolinguistics, and AI alignment that identifies the absence of unified frameworks for embedding cognition, culture, values, and cooperation into multi-agent LLM systems...

  18. Tractable Asymmetric Verification for Large Language Models via Deterministic Replicability

    cs.AI 2025-09 conditional novelty 3.0 of 10

    An LLM output can be verified by regenerating a few randomly chosen segments under identical hardware, with a tunable detection probability and 12.4x speedup over full regeneration.

Pith tools