arXiv:2605. 24197v2 Announce Type: replace Abstract: We study a class of emergent misalignment in multi-agent systems (MAS), with a focus on automated workflows, which we refer to agentic misalignment.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2606. 00765v1 Announce Type: new Abstract: LLM-based agents increasingly solve complex tasks through long trajectories involving reasoning steps, tool calls, and inter-agent communication.
arXiv:2606. 10747v1 Announce Type: new Abstract: As AI systems built from multiple language-model agents become more common, they are increasingly used to make decisions together: discussing, negotiating, and acting on shared tasks.
arXiv:2607. 07989v1 Announce Type: cross Abstract: Large language model (LLM) based multi-agent systems enable complex problem solving through coordinated reasoning and action, but their distributed structure also introduces new challenges in diagnosing system-level failures.
arXiv:2606. 03467v1 Announce Type: new Abstract: LLM-based multi-agent systems exhibit remarkable collaborative capabilities in complex multi-step tasks.
arXiv:2608. 06909v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate through long-horizon trajectories involving user instructions, tool use, external observations, and memory.
arXiv:2606. 07805v1 Announce Type: new Abstract: The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks.