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.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. 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.
DeFA is a dependency-guided framework that attributes failures in large language model agents by constructing an event dependency graph and a failure propagation graph from protocol relations and semantic dependencies. It identifies violating events, traces their sources and effects, and determines the decisive error, responsible agent, and error category. The method supports long trajectories through segmentation and has shown superior accuracy on text, image, and video tasks, while its diagnostic feedback can improve agent performance on subsequent tasks.
The paper introduces INTENT-AS-A-TOOL, a method that equips large language models with intent-targeted tools to provide a fine-grained, judge‑free signal of their commitment to specific behaviors during reasoning. By monitoring the probability of calling these intent tools, the authors can track how intent evolves throughout generation, complementing chain‑of‑thought monitoring and expanding post‑hoc labels into dense trajectories. The approach identifies critical steps for online intervention, demonstrating that action preferences are useful for detecting agentic misalignment in autonomous agents.
arXiv:2606. 03467v1 Announce Type: new Abstract: LLM-based multi-agent systems exhibit remarkable collaborative capabilities in complex multi-step tasks.