arXiv:2512.21794v3 Announce Type: replace-cross
Abstract: We study a sequential mechanism design problem in which a principal seeks to elicit truthful reports from multiple rational agents while starting with no prior knowledge of agents’ beliefs. We …
arXiv:2604.04503v3 Announce Type: replace
Abstract: Deep research agents (DRAs) integrate LLM reasoning with external tools. Memory systems enable DRAs to leverage historical experiences, which are essential for efficient reasoning and autonomous evol…
arXiv:2604.08944v1 Announce Type: new
Abstract: Multi-agent coordination under partial observability requires agents to share complementary private information. While recent methods optimize messages for intermediate objectives (e.g., reconstruction a…
arXiv:2510.07517v5 Announce Type: replace
Abstract: Multi-agent debate (MAD) aims to improve large language model (LLM) reasoning by letting multiple agents exchange answers and then aggregate their opinions. Yet recent studies reveal that agents are …
arXiv:2604.09028v1 Announce Type: cross
Abstract: Unmanned aerial vehicles serving as aerial base stations can rapidly restore connectivity after disasters, yet abrupt changes in user mobility and traffic demands shift the quality of service trade-off…
arXiv:2604.08963v1 Announce Type: cross
Abstract: While Multi-Agent Systems (MAS) are increasingly deployed for complex workflows, their emergent properties-particularly the accumulation of bias-remain poorly understood. Because real-world MAS are too…
arXiv:2403.19253v3 Announce Type: replace
Abstract: Effective agent coordination is crucial in cooperative Multi-Agent Reinforcement Learning (MARL). While agent cooperation can be represented by graph structures, prevailing graph learning methods in …
arXiv:2602.04418v3 Announce Type: replace-cross
Abstract: We present SPEAR, a multi-agent coordination framework for smart contract auditing that applies established MAS patterns in a realistic security analysis workflow. SPEAR models auditing as a co…
arXiv:2604.09523v1 Announce Type: new
Abstract: The transition of Multi-Agent Reinforcement Learning (MARL) policies from simulated cyber wargames to operational Security Operations Centers (SOCs) is fundamentally bottlenecked by the Sim2Real gap. Leg…
arXiv:2506.04676v2 Announce Type: replace-cross
Abstract: The data scarcity, label noise, and long-tailed category imbalance remain important and unresolved challenges in many computer vision tasks, such as object detection and instance segmentation, …