SwarmBench is a new benchmark designed to evaluate large language models (LLMs) as orchestrators of agent swarms, assessing accuracy, efficiency, cost, and process quality. The study finds significant variations in orchestration performance among current models, affecting not only final outcomes but also the quality of the orchestration process itself. To address these gaps, the authors introduce SwarmExp, a method that uses experience extraction and replay to consistently enhance LLM orchestration performance.
arXiv:2606. 13598v1 Announce Type: new Abstract: Multi-Agent Systems (MAS) built on Large Language Models (LLMs) require effective orchestration to coordinate specialized agents, yet training such orchestrators is hindered by limited supervision and high computational cost.
arXiv:2607. 02807v1 Announce Type: new Abstract: Long-running coding agents such as autoresearch can persistently discover optimizations for open-ended problems.
arXiv:2606. 13707v1 Announce Type: new Abstract: The recent success of agent swarms has shifted the paradigm of large language model (LLM)-based agents from single-agent workflows to multi-agent systems, highlighting the importance of agent orchestration for task decomposition and collaboration.
Harbor Adapters is a unified evaluation infrastructure that ports over 80 agentic benchmarks, enabling arbitrary agents to be tested across complex environments. The authors performed a large‑scale evaluation of 8 models on 54 benchmarks, using Terminus‑2 and three native harnesses, revealing detailed agent capabilities and failure modes. They also created Harbor‑Index, a curated set of 82 challenging tasks from 29 benchmarks, designed to be affordable yet comprehensive, with the best model achieving a 28.0% pass rate.
arXiv:2607. 25656v1 Announce Type: new Abstract: Complex tasks often decompose into parallelizable yet interdependent subtasks, making orchestration critical to the performance of multi-agent systems (MAS).
arXiv:2606.15872v2 Announce Type: replace Abstract: Frontier scientific reasoning remains a major challenge for large language models (LLMs), where even the strongest commercial systems fall short of...
arXiv:2606. 10662v1 Announce Type: cross Abstract: Multi-agent systems (MAS) can scale large language model reasoning at test time by decomposing complex problems into parallel subtasks.
arXiv:2606. 31564v1 Announce Type: new Abstract: The increasing complexity of agentic tasks has led to rapidly growing trajectory lengths, which poses significant challenges for large language model (LLM) based agents with fixed context windows.
arXiv:2606. 21228v2 Announce Type: replace Abstract: The capabilities of frontier Large Language Models (LLMs) continue to advance, with different providers increasingly specializing in distinct domains.
arXiv:2606. 18837v1 Announce Type: cross Abstract: Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks.
arXiv:2606. 12191v1 Announce Type: cross Abstract: Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities.
arXiv:2605.27898v3 Announce Type: replace Abstract: Agent benchmarks are increasingly used to compare large language models (LLMs) across domains, yet a reported score reflects a complete model--harn...