REVIEW 8 cited by
Single-agent or Multi-agent Systems? Why Not Both?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Single-agent or Multi-agent Systems? Why Not Both?
read the original abstract
Multi-agent systems (MAS) decompose complex tasks and delegate subtasks to different large language model (LLM) agents and tools. Prior studies have reported the superior accuracy performance of MAS across diverse domains, enabled by long-horizon context tracking and error correction through role-specific agents. However, the design and deployment of MAS incur higher complexity and runtime cost compared to single-agent systems (SAS). Meanwhile, frontier LLMs, such as OpenAI-o3 and Gemini-2.5-Pro, have rapidly advanced in long-context reasoning, memory retention, and tool usage, mitigating many limitations that originally motivated MAS designs. In this paper, we conduct an extensive empirical study comparing MAS and SAS across various popular agentic applications. We find that the benefits of MAS over SAS diminish as LLM capabilities improve, and we propose efficient mechanisms to pinpoint the error-prone agent in MAS. Furthermore, the performance discrepancy between MAS and SAS motivates our design of a hybrid agentic paradigm, request cascading between MAS and SAS, to improve both efficiency and capability. Our design improves accuracy by 1.1-12% while reducing deployment costs by up to 20% across various agentic applications.
Forward citations
Cited by 8 Pith papers
-
When Do Multi-Agent Systems Help? An Information Bottleneck Perspective
Multi-agent LLM systems help exactly when the context removed by compressed relays outweighs the downstream-relevant information those relays discard.
-
The Illusion of Multi-Agent Advantage
Automatically generated multi-agent systems underperform CoT-SC on benchmarks and a new diagnostic dataset, exposing architectural bloat that fails to deliver functional utility.
-
StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems
StepFinder turns execution logs into temporal semantic sequences via LLMs then uses temporal modeling plus attention to attribute failures to specific steps more accurately and 79% faster than direct LLM methods on th...
-
Towards Optimal Agentic Architectures for Offensive Security Tasks
Empirical comparison of agentic topologies for offensive security shows MAS-Indep reaching 64.2% validated detection while simpler baselines remain competitive on efficiency, with whitebox and web targets outperformin...
-
AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks
Single-agent LLM frameworks outperform naive multi-agent systems in multimodal clinical risk prediction tasks and are better calibrated.
-
The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG Systems
Single-agent RAG matches multi-agent lexical quality for README generation at 86% lower token use and double speed, with MAS at 98% structural consistency and developer-guided plans producing the highest quality.
-
The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG Systems
Single-agent RAG pipeline matches multi-agent lexical quality for README generation while cutting token consumption by 86% and doubling speed, with developer-guided planning yielding the highest overall quality.
-
Towards Multi-Agent Autonomous Reasoning in Hydrodynamics
A Layer Execution Graph multi-agent system for hydrodynamics achieves 93.6% factual precision and 100% pass rate on 37 queries while degrading gracefully under data loss.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.