Pith. sign in

REVIEW 17 cited by

G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks

Not yet reviewed by Pith; the record is open.

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 2410.11782 v3 pith:ORW57WEI submitted 2024-10-15 cs.MA cs.LG

classification cs.MAcs.LG
keywords communicationg-designermulti-agentagentshigh-performingtasktextbftopologies
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, primarily due to well-crafted inter-agent communication topologies. Despite the diverse and high-performing designs available, practitioners often face confusion when selecting the most effective pipeline for their specific task: \textit{Which topology is the best choice for my task, avoiding unnecessary communication token overhead while ensuring high-quality solution?} In response to this dilemma, we introduce G-Designer, an adaptive, efficient, and robust solution for multi-agent deployment, which dynamically designs task-aware, customized communication topologies. Specifically, G-Designer models the multi-agent system as a multi-agent network, leveraging a variational graph auto-encoder to encode both the nodes (agents) and a task-specific virtual node, and decodes a task-adaptive and high-performing communication topology. Extensive experiments on six benchmarks showcase that G-Designer is: \textbf{(1) high-performing}, achieving superior results on MMLU with accuracy at $84.50\%$ and on HumanEval with pass@1 at $89.90\%$; \textbf{(2) task-adaptive}, architecting communication protocols tailored to task difficulty, reducing token consumption by up to $95.33\%$ on HumanEval; and \textbf{(3) adversarially robust}, defending against agent adversarial attacks with merely $0.3\%$ accuracy drop.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 17 Pith papers

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

  1. MasFACT: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    MasFACT transfers historical topology priors across tasks via Fused Gromov-Wasserstein optimal transport and PAC-Bayes conservative adaptation to reduce topology forgetting in continual multi-agent settings.

  2. Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration

    cs.AI 2025-11 conditional novelty 6.0 of 10

    A state-aware contrastive router that selects the most relevant agent at each step improves multi-agent LLM accuracy by up to 23.8% while using a fraction of the tokens of fixed-pipeline baselines.

  3. MASPRM: Multi-Agent System Process Reward Model

    cs.MA 2025-10 conditional novelty 6.0 of 10

    MASPRM trains a per-agent, per-message value head from outcome-only MCTS rollouts and uses it to guide step-level beam search and MCTS, improving exact match on GSM8K by up to +30.7 points over a greedy multi-agent pass.

  4. SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A history-aware guard model with an LLM judge is reported to cut jailbreak success on mobile agent tasks from 86.1% to 8.4% while keeping task completion unchanged at 77.8%.

  5. MasHost Builds It All: Autonomous Multi-Agent System Directed by Reinforcement Learning

    cs.MA 2025-06 conditional novelty 6.0 of 10

    MasHost uses reinforcement learning to autonomously construct query-adaptive multi-agent graphs, and its authors report the best average accuracy across six LLM benchmarks.

  6. G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems

    cs.MA 2025-06 conditional novelty 6.0 of 10

    G-Memory stores past multi-agent teamwork in a three-tier graph and retrieves it to boost performance on five benchmarks.

  7. Adaptive Graph Pruning for Multi-Agent Communication

    cs.CL 2025-06 conditional novelty 6.0 of 10

    AGP trains a graph neural network to jointly decide which agents to keep and how strongly they should communicate, and reports state-of-the-art average accuracy across six LLM benchmarks with large token savings.

  8. Transition from Statistical to Hardware-Limited Scaling in Photonic Quantum State Reconstruction

    quant-ph 2026-03 unverdicted novelty 5.0 of 10

    Classical shadow tomography on integrated photonics shows a sharp transition from statistical O(M^{-1/2}) error scaling to a hardware-limited floor set by unitary spectral distortions.

  9. Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models

    cs.IR 2026-01 reject novelty 5.0 of 10

    A two-framework testbed comparison claims mem0 is Pareto-optimal over Graphiti for distributed LLM agents because its lower cost is paired with accuracy that is not significantly different.

  10. Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities

    cs.AI 2025-06 conditional novelty 5.0 of 10

    A survey that groups graph-empowered AI agent research into planning, execution, memory, and multi-agent coordination, plus agents-for-graphs and applications.

  11. We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems

    cs.LG 2025-06 conditional novelty 5.0 of 10

    MCP-powered LLM agents are vulnerable to prompt injection from third-party services, and simple detection or filtering defenses do not reliably stop these attacks.

  12. MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Encoding LLM agent workflows as statically checked Mermaid graphs and evolving them with constrained mutations improves solve rates on GSM8K, MATH, HumanEval, and MBPP.

  13. CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A student-teacher multi-agent pipeline with positive-only feedback improves QWK agreement with human essay scores by 21% on a multimodal benchmark, with gains concentrated in traits where baselines were weakest.

  14. ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization

    cs.CL 2025-02 conditional novelty 5.0 of 10

    ScoreFlow uses a score-weighted variant of direct preference optimization to automatically generate and refine per-task LLM agent workflows, reporting an average 8.2% improvement over baselines on six benchmarks.

  15. Self-Evolving Coding Agents

    cs.SE 2026-08 conditional novelty 4.0 of 10

    A systematic survey that defines self-evolving coding agents, organizes systems into a five-category object-centered taxonomy, and analyzes when and on what evidence these agents evolve.

  16. GEMMAS: Graph-based Evaluation Metrics for Multi Agent Systems

    cs.CL 2025-07 reject novelty 4.0 of 10

    GEMMAS proposes two graph-based metrics for multi-agent LLM collaboration, but its redundancy metric is defined using ground-truth answer correctness rather than actual information redundancy.

  17. Mathematical methods of reinforcement learning

    math.OC 2026-07 accept

    A survey unifying the operator-theoretic, probabilistic, and optimization-based mathematical structures underlying modern reinforcement learning algorithms.

Pith tools