MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Mao-xun Huang, Jerry Wang, Yi-Cheng Lai, Zhengxin Zhang, Claire Cardie, Hen-Hsen Huang
• Venue: arXiv: cs.AI
• Published: 2026-07-30
• Collected: 2026-07-31
• URL: http://arxiv.org/abs/2607.28527v1
• PDF: https://arxiv.org/pdf/2607.28527v1
• DOI: UNKNOWN

Plain-Language Brief

The paper introduces MANTA, a framework for adapting communication structures in multi-agent systems during inference time. This allows for more efficient problem solving by enabling agents to adjust their roles, links, execution order, and validation pathways as needed, while preserving the task interface and agent budget.

What the Document Says

• The paper presents MANTA, a framework for Multi-Agent Network Topology Adaptation.
• MANTA allows communication structures to self-evolve at inference time.
• Before execution, MANTA initializes a task-conditioned topology from prior structural experience.
• During deployment, it monitors collaboration traces and applies bounded structural updates when the current organization becomes insufficient.
• These updates can modify agent roles, communication links, execution order, information visibility, and validation pathways.
• MANTA preserves the task interface and agent budget.
• The paper evaluates MANTA against several baselines on five benchmarks spanning various tasks.
• MANTA achieves the highest average score of 74.0, outperforming the strongest baseline by 5.8 percentage points.
• MANTA obtains the best result on PlanCraft.

Key Concepts Mentioned

• Multi-Agent Network Topology Adaptation
• Self-evolving Multi-Agent Systems
• Task decomposition
• Agent specialization
• Information exchange
• Intermediate validation

Claims Made by the Document

• MANTA improves complex problem solving.
• Existing systems typically treat communication topology as a fixed design choice or an offline optimization target.
• MANTA outperforms the strongest baseline by 5.8 percentage points.
• MANTA obtains the best result on PlanCraft.

Evidence Used

• Improvement is shown through the high average score of 74.0 achieved by MANTA.
• The comparison with baselines demonstrates that MANTA outperforms the strongest baseline and obtains the best result on PlanCraft.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Large language model-based multi-agent systems improve complex problem solving through task decomposition, agent specialization, information exchange, and intermediate validation. However, existing systems typically treat communication topology as a fixed design choice or an offline optimization target. We introduce MANTA, a framework for Multi-Agent Network Topology Adaptation that enables communication structures to self-evolve at inference time. Before execution, MANTA initializes a task-conditioned topology from prior structural experience. During deployment, it monitors collaboration traces and applies bounded structural updates when the current organization becomes insufficient. These updates can modify agent roles, communication links, execution order, information visibility, and validation pathways while preserving the task interface and agent budget. We evaluate MANTA against representative single-agent and multi-agent baselines on five benchmarks spanning information seeking, tool use, planning, workflow execution, and mathematical reasoning. MANTA achieves the highest average score of 74.0, outperforming the strongest baseline by 5.8 percentage points and obtaining the best result on PlanCraft. These results show that inference-time self-improvement can extend to the architecture of collaboration itself.