The paper introduces Multi-View Evidential (MVE) learning for evaluating trustworthiness of collaborators in distributed systems. It models each task owner’s interaction as an independent view, uses the Mamba model to capture temporal trust dynamics, and applies evidential deep learning to quantify uncertainty. A dynamic fusion strategy then combines view-specific evidence to produce a final trust assessment, outperforming baselines in accuracy and task success rate.
By Botao Zhu, Xianbin Wang
The paper introduces a bidirectional Mamba-enabled model (BM) for long‑term behavioral evaluation of devices in collaborative tasks. By constructing short‑time‑slot graphs of device interactions and aggregating behavioral features, BM integrates forward and backward temporal dependencies across all intervals. Experiments show that BM outperforms baseline methods, improving the accuracy of selecting trustworthy collaborators to maximize task completion value.
By Botao Zhu, Xianbin Wang
arXiv:2606. 06388v1 Announce Type: new Abstract: Recent advances in LLM agents have enabled complex cognitive capabilities, such as multi-step reasoning, planning, and tool use, that increasingly position these agents as human collaborators.
By Jiaju Chen, Yuxuan Lu, Jiayi Su, Chaoran Chen, Songlin Xiao, Zheng Zhang, Yun Wang, Yunyao Li, Jian Zhao, Tongshuang Wu, Toby Jia-Jun Li, Dakuo Wang, Bingsheng Yao
Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these networks, everyday tool use becomes multi-party owned-agent collaboration over personal workspaces, where files, records, tools, and policies are not directly visible across owners.
The paper proposes a mental model-based framework of trust that captures multidimensional aspects of trust and can be used to infer human trust in AI agents. It formalizes trust perception, trust evolution, human reliance, and decision-making, and defines the appropriate level of trust in the agent. Human subject studies evaluate whether adjusting human beliefs about the agent, as predicted by the framework, can change trust perceptions across performance, process, and purpose dimensions.
By Zahra Zahedi, Sarath Sreedharan, Erin Chiou, Subbarao Kambhampati
arXiv:2606. 14923v1 Announce Type: new Abstract: As language-model agents increasingly work in teams, each agent must decide how much to trust its teammates.
By Yujiao Chen