mlsanityData to 14 Oct 2026

Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems

arXiv 2505.12467 ↗First posted 18 May 2025cs.MA cs.AIcited by 3

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Multi-agent collaboration has emerged as a pivotal paradigm for addressing complex, distributed tasks in large language model (LLM)-driven applications. While prior research has focused on high-level architectural frameworks, the granular mechanisms governing agents, critical to performance and scalability, remain underexplored. This study systematically investigates four dimensions of collaboration strategies: (1) agent governance, (2) participation control, (3) interaction dynamics, and (4) dialogue history management. Through rigorous experimentation under two context-dependent scenarios: Distributed Evidence Integration (DEI) and Structured Evidence Synthesis (SES), we quantify the impact of these strategies on both task accuracy and computational efficiency. Our findings reveal that centralized governance, instructor-led participation, ordered interaction patterns, and instructor-curated context summarization collectively optimize the trade-off between decision quality and resource utilization with the support of the proposed Token-Accuracy Ratio (TAR). This work establishes a foundation for designing adaptive, scalable multi-agent systems, shifting the focus from structural novelty to strategic interaction mechanics.

Key facts. Cited by 3 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 8 of its 23 references that are in the map. First posted on arXiv 18 May 2025.

Builds on

8 of 23 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Multi-Agent Collaboration via Cross-Team Orchestration13 Jun
  2. 2024Scaling Large Language Model-based Multi-Agent Collaboration11 Jun
  3. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug

Other references · 5

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  3. 2021AmbiFC: Fact-Checking Ambiguous Claims with Evidencecited by 38
  4. 2024Beyond Direct Diagnosis: LLM-based Multi-Specialist Agent Consultation for Automatic Diagnosiscited by 23
  5. 2023Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinesecited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Beyond Isolated Investor: Predicting Startup Success via Roleplay-Based Collective Agentscited by 1
  2. 2026Communication Enhances LLMs' Stability in Strategic Thinkingcited by 1
  3. 2026Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaborationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  2. 2026Rethinking Multi-Agent Collaboration: When More Is Less
  3. 2026Scaling Behavior of Single LLM-Driven Multi-Agent Systems
  4. 2025Modeling Response Consistency in Multi-Agent LLM Systems: A Comparative Analysis of Shared and Separate Context Approaches
  5. 2026Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor
  6. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
  7. 2025Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes
  8. 2026Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs