arXiv AI
Jul 20
When Do Multi-Agent Systems Help? An Information Bottleneck Perspective
arXiv:2607. 16133v1 Announce Type: cross Abstract: LLM powered multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks.
How Task Structure Limits Multi-Agent Success: An Information-Theoretic Analysis
arXiv:2606. 13733v1 Announce Type: cross Abstract: Multi-agent systems (MAS) were expected to overcome the limitation of single-agent systems (SAS) through collaboration.
Related stories
arXiv AI
Jun 2
Scaling Behavior of Single LLM-Driven Multi-Agent Systems
arXiv:2606. 00655v1 Announce Type: cross Abstract: The burgeoning field of LLM-based Multi-Agent Systems (MAS) promises to tackle complex tasks through collaborative intelligence, yet fundamental questions regarding their scaling behavior and intrinsic collective dynamics remain underexplored.
arXiv AI
Aug 11
The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation
arXiv:2511. 02687v2 Announce Type: replace Abstract: The trajectory of AI development suggests that we will increasingly rely on agent-based systems powered by language models, composed of independently developed agents with different information, privileges, and tools.
arXiv AI
Aug 25
The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams
arXiv:2608.23541v1 Announce Type: cross Abstract: Does multi-agent LLM interaction help or hurt? Some work reports gains from debate (Du et al., 2024), critique loops (Chen et al., 2025), and mixture...
arXiv AI
Jun 8
When Does Multi-Agent Collaboration Help? An Entropy Perspective
arXiv:2602. 04234v6 Announce Type: cross Abstract: Multi-agent systems (MAS) have emerged as a prominent paradigm for leveraging large language models (LLMs) to tackle complex tasks.
arXiv Computation and Language
Sep 1
AlgoWorlds: Benchmarking Tool Use for Global Optimization in Algorithmic Worlds
arXiv:2608.29397v1 Announce Type: new Abstract: Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments. However, feasibility alone is...
arXiv AI
Jul 16
Benefits and Limitations of Communication in Multi-Agent Reasoning
arXiv:2510. 13903v2 Announce Type: replace-cross Abstract: Chain-of-thought prompting has popularized step-by-step reasoning in large language models, yet model performance still degrades as problem complexity and context length grow.
arXiv AI
Aug 14
Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference
arXiv:2608. 12921v1 Announce Type: cross Abstract: The performance of large language model (LLM)-based multi-agent systems (MAS) largely depends on effective communication topologies.
arXiv Computation and Language
Sep 23
Agensh: Scaling Organizational Intelligence to 1,024 Agents
Agensh is a new multi‑agent harness that eliminates a central orchestrator by letting workers self‑organize through a continuous cooperation loop. The system uses a shared workspace, message interface, and shared context to coordinate tasks, verify results, and merge progress asynchronously. Experiments on ProgramBench and pandoc show that scaling from 1 to 1,024 agents improves test‑pass rates by up to 49% relative, demonstrating that agent count is a viable scaling dimension for complex tasks.
arXiv AI
Jul 15
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
arXiv:2607. 13034v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires.
arXiv AI
Aug 6
Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection
arXiv:2608. 05085v1 Announce Type: cross Abstract: Systems that automate scientific discovery must repeatedly decide which experiment to run, which hypothesis to test, which tool to build, and when to stop.
arXiv Machine Learning
Jun 2
Multi-Agent Computer Use
arXiv:2606. 01533v1 Announce Type: cross Abstract: Computer use agents (CUAs) today are primarily deployed as single serial agents.