mlsanityData to 14 Oct 2026

Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence

arXiv 2512.08743 ↗First posted 9 Dec 2025cs.AI cs.MAcited by 0

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

Abstract (arXiv)

Foundation models (FMs) are increasingly assuming the role of the ''brain'' of AI agents. While recent efforts have begun to equip FMs with native single-agent abilities -- such as GUI interaction or integrated tool use -- we argue that the next frontier is endowing FMs with native multi-agent intelligence. We identify four core capabilities of FMs in multi-agent contexts: understanding, planning, efficient communication, and adaptation. Contrary to assumptions about the spontaneous emergence of such abilities, we provide extensive empirical evidence, across 41 large language models and 7 challenging benchmarks, showing that scaling single-agent performance alone does not automatically yield robust multi-agent intelligence. To address this gap, we outline key research directions -- spanning dataset construction, evaluation, training paradigms, and safety considerations -- for building FMs with native multi-agent intelligence.

Key facts. No citing papers in the map yet (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 31 of its 47 references that are in the map. First posted on arXiv 9 Dec 2025.

Builds on

31 of 47 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Large Language Models Miss the Multi-Agent Mark27 May
  2. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges15 May
  3. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  4. 2023LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models5 Oct
  5. 2023ProAgent: Building Proactive Cooperative Agents with Large Language Models22 Aug

Other references · 26

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2020Scaling Laws for Neural Language Modelscited by 6,586
  4. 2023Let's Verify Step by Stepcited by 3,789
  5. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  6. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  7. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  8. 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 672
  9. 2025Why Do Multi-Agent LLM Systems Fail?cited by 604
  10. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 523
  11. 2017Population Based Training of Neural Networkscited by 367
  12. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 222
14 more
  1. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 209
  2. 2025Multi-Agent Risks from Advanced AIcited by 163
  3. 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganographycited by 113
  4. 2023Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approachcited by 79
  5. 2024ToMBench: Benchmarking Theory of Mind in Large Language Modelscited by 72
  6. 2019Learning Efficient Multi-agent Communication: An Information Bottleneck Approachcited by 61
  7. 2024SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMscited by 57
  8. 2024EmoBench: Evaluating the Emotional Intelligence of Large Language Modelscited by 53
  9. 2019Biases for Emergent Communication in Multi-agent Reinforcement Learningcited by 48
  10. 2022Model-Free Opponent Shapingcited by 44
  11. 2024Epistemic Injustice in Generative AIcited by 16
  12. 2024FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learningcited by 13
  13. 2024Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmascited by 12
  14. 2025PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environmentscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards a Science of Scaling Agent Systems
  2. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
  3. 2025Towards General Agentic Intelligence via Environment Scaling
  4. 2026Scaling Behavior of Single LLM-Driven Multi-Agent Systems
  5. 2026Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
  6. 2026Orchestrating Intelligence: Confidence-Aware Routing for Efficient Multi-Agent Collaboration across Multi-Scale Models
  7. 2026Can Small Agents Collaborate to Beat a Single Large Language Model?
  8. 2026Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence