Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems
National University of Singapore(国立新加坡大学);Singapore University of Technology(新加坡科技学院);Nanyang Technological University(南洋理工大学);Duke University(杜克大学);University of Waterloo(滑铁卢大学);Microsoft(微软公司);Peking University(北京大学);University of Pennsylvania(宾夕法尼亚大学)
Individual agents in multi-agent (MA) systems often lack robustness, tending to blindly conform to misleading peers. We show this weakness stems from both sycophancy and inadequate ability to evaluate peer reliability. To address this, we first formalize the learning problem of history-aware reference, introducing the historical interactions of peers as additional input, so that agents can estimate peer reliability and learn from trustworthy peers when uncertain. This shifts the task from evaluating peer reasoning quality to estimating peer reliability based on interaction history. We then develop Epistemic Context Learning (ECL): a reasoning framework that conditions predictions on explicitly-built peer profiles from history. We further optimize ECL by reinforcement learning using auxiliary rewards. Our experiments reveal that our ECL enables small models like Qwen 3-4B to outperform a history-agnostic baseline 8x its size (Qwen 3-30B) by accurately identifying reliable peers. ECL also boosts frontier models to near-perfect (100%) performance. We show that ECL generalizes well to various MA configurations and we find that trust is modeled well by LLMs, revealing a strong correlation in trust modeling accuracy and final answer quality.
University of Southern California(南加州大学);McGill University(麦吉尔大学);UC Berkeley(加州大学伯克利分校);Vector Institute(向量研究所);Cardiff University(卡迪夫大学);University College London(伦敦大学学院);IIIT Hyderabad(海得拉巴印度理工学院);Harvard University(哈佛大学);Université de Montréal(蒙特利尔大学);Mila
The Temporal Dynamics of Belief-based Updating of Epistemic Trust: Light at the End of the Tunnel?
Ludwig-Maximilians-University of Munich (LMU)(慕尼黑大学(LMU));Friedrich Alexander University Erlangen-Nürnberg(埃尔朗根-纽伦堡弗里德里希·亚历山大大学);Birkbeck College London(伦敦伯克贝克学院)
Scientific Explanations in Health Sciences: Causality, Trust, and Epistemic Adequacy
College of Mathematical Medicine, Zhejiang Normal University(浙江师范大学数学医学院);DAIS, Ca’ Foscari University of Venice(威尼斯大学DAIS);European Centre for Living Technology(欧洲生命技术中心)
Handling Epistemic and Aleatory Uncertainties in Probabilistic Circuits
Università degli Studi di Brescia(布雷西亚大学);Cardiff University(卡迪夫大学);CCDC Army Research Laboratory(CCDC陆军研究实验室);KU Leuven(鲁汶大学);Blue Prism AI Labs(蓝棱镜人工智能实验室);Ozyegin University(奥兹耶金大学)
Anthropomorphism and Trust in Human-Large Language Model interactions
Brain and Creativity Institute, Dornsife College of Letters, Arts and Sciences, University of Southern California(脑与创造力研究所,文理学院,南加州大学);USC Mrs. T.H. Chan Division of Occupational Science and Occupational Therapy, University of Southern California(USC 玛丽·T.H.陈职业科学与职业治疗 division,南加州大学);Psychiatry and Biobehavioral Sciences, David Geffen School of Medicine, University of California, Los Angeles(精神病学与生物行为科学,大卫·格芬医学院,加州大学洛杉矶分校);Google DeepMind, Zurich(谷歌深Mind,苏黎世);Google Research(谷歌研究);Brain and Creativity Institute(脑与创造力研究所)
"I can assure you [$\ldots$] that it's going to be all right" -- A definition, case for, and survey of algorithmic assurances in human-autonomy trust relationships
The Generative AI Paradox: GenAI and the Erosion of Trust, the Corrosion of Information Verification, and the Demise of Truth
Thomas Lord Department of Computer Science, University of Southern California (USC)(汤姆斯·劳德计算机科学系,南加州大学);Information Sciences Institute (ISI), University of Southern California (USC)(信息科学研究所,南加州大学)
"Dave...I can assure you...that it's going to be all right..." -- A definition, case for, and survey of algorithmic assurances in human-autonomy trust relationships
University of Colorado Boulder(科罗拉多大学博尔德分校);Cooperative Human-Robot Intelligence Laboratory(人机协作智能实验室);Research and Engineering Center for Unmanned Vehicles(无人驾驶车辆研究与工程中心)