Lune

ACL Findings2026

Superficial Success vs. Internal Breakdown: An Empirical Study of Generalization in Adaptive Multi-Agent Systems

Namyeong So, Seokgyu Jang, Taeuk Kim

Abstract

Adaptive multi-agent systems (MAS) are increasingly adopted to tackle complex problems. However, the narrow task coverage of their optimization raises the question of whether they can function as general-purpose systems. To address this gap, we conduct an extensive empirical study of adaptive MAS, revealing two key findings: (1) topological overfitting-they fail to generalize across different domains; and (2) illusory coordination-they achieve reasonable surface-level accuracy while the underlying agent interactions diverge from ideal MAS behavior, raising concerns about their practical utility. These findings highlight the pressing need to prioritize generalization in MAS development and motivate evaluation protocols that extend beyond simple final-answer correctness.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on15

  1. Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
  2. AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent BehaviorsWeize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang et al.ICLR 2024 · 594 citations
  3. Debating with More Persuasive LLMs Leads to More Truthful AnswersAkbir Khan, John Hughes, Dan Valentine, Laura Ruis et al.ICML 2024 · 244 citations
  4. SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language ModelsXiaoxuan Wang, Ziniu Hu, Pan Lu, Yanqiao Zhu et al.ICML 2024 · 220 citations
  5. GPTSwarm: Language Agents as Optimizable GraphsMingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio et al.ICML 2024 · 45 citations

Related papers

  1. Architecture Matters for Multi-Agent SecurityBen Hagag, William Anderson, Christian Schroeder de Witt, Sarah SchefflerICML 2026 · 1 citation
  2. MAS-Architect: Declarative Multi-Agent System Design via Separation of ConcernsJing Huang, Lidong Zhang, Mutian Bao, Yadong Li et al.ICML 2026
  3. Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea GenerationNuo Chen, Yicheng Tong, Yuzhe Yang, Yufei He et al.ACL Findings 2026 · 1 citation
  4. OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative ModelsShiyuan Li, Yixin Liu, Yu Zheng, Mei Li et al.WWW 2026 · 2 citations
  5. MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled BenchmarksZixuan Ke, Yifei Ming, Austin Xu, Ryan Chin et al.ICML 2026 · 15 citations
Dusk over the sea between two cliffs drawn in fine vertical lines