When Do Multi-Agent Systems Outperform? Analysing the Learning Efficiency of Agentic Systems

• URL: http://arxiv.org/abs/2602.08272v1
• Date: Mon, 09 Feb 2026 05:08:36 GMT
• Title: When Do Multi-Agent Systems Outperform? Analysing the Learning Efficiency of Agentic Systems
• Authors: Junwei Su, Chuan Wu,
• Abstract summary: Multi-Agent Reinforcement Learning (MARL) offers a promising avenue by decomposing complex tasks into specialized subtasks.<n>This paper rigorously analyzes the comparative sample efficiency of MARL and Single-Agent RL (SARL) within the context of large language models (LLMs)<n>Our results demonstrate that MARL improves sample complexity when tasks naturally decompose into independent subtasks, whereas dependent subtasks diminish MARL's comparative advantage.
• Score: 19.835807214272457
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning (RL) has emerged as a crucial method for training or fine-tuning large language models (LLMs), enabling adaptive, task-specific optimizations through interactive feedback. Multi-Agent Reinforcement Learning (MARL), in particular, offers a promising avenue by decomposing complex tasks into specialized subtasks learned by distinct interacting agents, potentially enhancing the ability and efficiency of LLM systems. However, theoretical insights regarding when and why MARL outperforms Single-Agent RL (SARL) remain limited, creating uncertainty in selecting the appropriate RL framework. In this paper, we address this critical gap by rigorously analyzing the comparative sample efficiency of MARL and SARL within the context of LLM. Leveraging the Probably Approximately Correct (PAC) framework, we formally define SARL and MARL setups for LLMs, derive explicit sample complexity bounds, and systematically characterize how task decomposition and alignment influence learning efficiency. Our results demonstrate that MARL improves sample complexity when tasks naturally decompose into independent subtasks, whereas dependent subtasks diminish MARL's comparative advantage. Additionally, we introduce and analyze the concept of task alignment, quantifying the trade-offs when enforcing independent task decomposition despite potential misalignments. These theoretical insights clarify empirical inconsistencies and provide practical criteria for deploying MARL strategies effectively in complex LLM scenarios.

Related papers

• LLM-FS-Agent: A Deliberative Role-based Large Language Model Architecture for Transparent Feature Selection [0.0]
  This paper introduces LLM-FS-Agent, a novel multi-agent architecture designed for interpretable and robust feature selection.<n>We evaluate LLM-FS-Agent in the cybersecurity domain using the CIC-DIAD 2024 IoT intrusion detection dataset.
  arXiv  Detail & Related papers  (2025-10-07T13:46:06Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• RLAE: Reinforcement Learning-Assisted Ensemble for LLMs [21.77261258691006]
  Large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks.<n>We propose Reinforcement Learning-Assisted Ensemble for LLMs, a novel framework that reformulates ensemble through the lens of a Markov Decision Process (MDP)<n>Our approach introduces a RL agent that dynamically adjusts ensemble weights by considering both input context and intermediate generation states.
  arXiv  Detail & Related papers  (2025-05-31T07:38:41Z)
• Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL [62.984693936073974]
  Large language models (LLMs) excel in tasks like question answering and dialogue.<n>Complex tasks requiring interaction, such as negotiation and persuasion, require additional long-horizon reasoning and planning.<n>We propose a novel approach that uses goal-conditioned value functions to guide the reasoning of LLM agents.
  arXiv  Detail & Related papers  (2025-05-23T16:51:54Z)
• LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities [21.42711537107199]
  We study why Large Language Models (LLMs) perform sub-optimally in decision-making scenarios.<n>We propose mitigation of these shortcomings by fine-tuning via Reinforcement Learning (RL) on self-generated CoT rationales.
  arXiv  Detail & Related papers  (2025-04-22T17:57:14Z)
• Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
  Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.<n>Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.<n>We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
  arXiv  Detail & Related papers  (2025-02-04T17:26:58Z)
• EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration [76.66831821738927]
  Large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty.<n>We measure LLMs' (in)ability to make optimal decisions in bandits, a state-less reinforcement learning setting relevant to many applications.<n>Motivated by the existence of optimal exploration algorithms, we propose efficient ways to integrate this algorithmic knowledge into LLMs.
  arXiv  Detail & Related papers  (2024-10-08T17:54:03Z)
• Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
  Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning. We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
  arXiv  Detail & Related papers  (2024-06-20T13:08:09Z)
• Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning [10.186029242664931]
  We present MAPO-LSO which applies a form of comprehensive representation learning devised to supplement MARL training. Specifically, MAPO-LSO proposes a multi-agent extension of transition dynamics reconstruction and self-predictive learning. Empirical results demonstrate MAPO-LSO to show notable improvements in sample efficiency and learning performance compared to its vanilla MARL counterpart.
  arXiv  Detail & Related papers  (2024-06-05T03:11:44Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [68.29746557968107]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans.<n> Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.