From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；State Key Laboratory of Complex System Modeling and Simulation Technology（复杂系统建模与仿真技术国家重点实验室）；Science & Technology on Integrated Information System Laboratory（信息系统集成技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Wuhan University of Technology（武汉理工大学）
LLM-powered Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex domains but suffer from inherent fragility and opaque failure mechanisms. Existing failure attribution methods, whether relying on direct prompting, costly replays, or supervised fine-tuning, typically treat execution logs as flat sequences. This linear perspective fails to disentangle the intricate causal links inherent to MAS, leading to weak observability and ambiguous responsibility boundaries. To address these challenges, we propose CHIEF, a novel framework that transforms chaotic trajectories into a structured hierarchical causal graph. It then employs hierarchical oracle-guided backtracking to efficiently prune the search space via sybthesized virtual oracles. Finally, it implements counterfactual attribution via a progressive causal screening strategy to rigorously distinguish true root causes from propagated symptoms. Experiments on Who&When benchmark show that CHIEF outperforms eight strong and state-of-the-art baselines on both agent- and step-level accuracy. Ablation studies further confirm the critical role of each proposed module.
DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；School of New Media and Communication, Tianjin University（天津大学新媒体与传播学院）；College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学技术与人工智能学院）
HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI Systems
Harokopio University of Athens（雅典哈罗科皮奥大学）；Democritus University of Thrace（色雷斯德谟克利特大学）；University of Western Macedonia（西马其顿大学）；Athena Research Center（雅典娜研究中心）
Bar Ilan University（巴伊兰大学）；Allen Institute for AI（艾伦人工智能研究所）
We find that the requirement of model interpretations to be faithful is vague and incomplete. With interpretation by textual highlights as a case-study, we present several failure cases. Borrowing concepts from social science, we identify that the problem is a misalignment between the causal chain of decisions (causal attribution) and the attribution of human behavior to the interpretation (social attribution). We re-formulate faithfulness as an accurate attribution of causality to the model, and introduce the concept of aligned faithfulness: faithful causal chains that are aligned with their …
Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）
Actual causality and a closely related concept of responsibility attribution are central to accountable decision making. Actual causality focuses on specific outcomes and aims to identify decisions (actions) that were critical in realizing an outcome of interest. Responsibility attribution is complementary and aims to identify the extent to which decision makers (agents) are responsible for this outcome. In this paper, we study these concepts under a widely used framework for multi-agent sequential decision making under uncertainty: decentralized partially observable Markov decision processes …
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Alibaba Inc（阿里巴巴集团）
Multi-touch attribution (MTA), aiming to estimate the contribution of each advertisement touchpoint in conversion journeys, is essential for budget allocation and automatically advertising. Existing methods first train a model to predict the conversion probability of the advertisement journeys with historical data and calculate the attribution of each touchpoint using counterfactual predictions. An assumption of these works is the conversion prediction model is unbiased, i.e., it can give accurate predictions on any randomly assigned journey, including both the factual and counterfactual ones.…
SKEMA Business School（SKEMA商学院）；Millennium Institute for Foundations of Data Research（千禧数据基础研究所）
In this expository article we highlight the relevance of explanations for artificial intelligence, in general, and for the newer developments in {\em explainable AI}, referring to origins and connections of and among different approaches. We describe in simple terms, explanations in data management and machine learning that are based on attribution-scores, and counterfactuals as found in the area of causality. We elaborate on the importance of logical reasoning when dealing with counterfactuals, and their use for score computation.
Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths
KU Leuven（KU Leuven（天主教鲁汶大学））；Laboratory of Multi-omics Integrative Bioinformatics（多组学整合生物信息学实验室）；KU Leuven Institute for Single Cell Omics (LISCO)（KU Leuven单细胞组学研究所（LISCO））；Department of Electrical Engineering, KU Leuven（KU Leuven电气工程系）；Department of Development and Regeneration, KU Leuven（KU Leuven发育与再生系）
Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）
Responsibility attribution is a key concept of accountable multi-agent decision making. Given a sequence of actions, responsibility attribution mechanisms quantify the impact of each participating agent to the final outcome. One such popular mechanism is based on actual causality, and it assigns (causal) responsibility based on the actions that were found to be pivotal for the considered outcome. However, the inherent problem of pinpointing actual causes and consequently determining the exact responsibility assignment has shown to be computationally intractable. In this paper, we aim to provid…
With the increasing adoption of predictive models trained using machine learning across a wide range of high-stakes applications, e.g., health care, security, criminal justice, finance, and education, there is a growing need for effective techniques for explaining such models and their predictions. We aim to address this problem in settings where the predictive model is a black box; That is, we can only observe the response of the model to various inputs, but have no knowledge about the internal structure of the predictive model, its parameters, the objective function, and the algorithm used t…
We tackle the challenge of in-session attribution for on-site search engines in eCommerce. We phrase the problem as a causal counterfactual inference, and contrast the approach with rule-based systems from industry settings and prediction models from the multi-touch attribution literature. We approach counterfactuals in analogy with treatments in formal semantics, explicitly modeling possible outcomes through alternative shopper timelines; in particular, we propose to learn a generative browsing model over a target shop, leveraging the latent space induced by prod2vec embeddings; we show how n…
Computational Copyright: Towards A Royalty Model for Music Generative AI
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Michigan（密歇根大学）；Harvard University（哈佛大学）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）；Carnegie Mellon University（卡内基梅隆大学）
Hidden Heroes and Gradient Bloats: Layer-Wise Redundancy Inverts Attribution in Transformers
Department of Computer Science, Fu Foundation School of Engineering and Applied Science, Columbia University, New York, NY, USA（计算机科学系，工程与应用科学基金会学院，哥伦比亚大学，纽约，纽约州，美国）
From Graphs to Gradients: Physics-Inspired Structural Attribution for Cyber-Physical IoT Systems and Beyond
Research & Innovation Development Department, Netcompany S.A.（研究与创新发展部，Netcompany S.A.公司）；Department of Informatics and Telematics, Harokopio University of Athens（雅典哈罗科皮奥大学信息学与电信系）；Department of Electrical and Computer Engineering, Hellenic Mediterranean University（希腊地中海大学电气与计算机工程系）；Department of Electrical and Computer Engineering, University of Western Macedonia（西马其顿大学电气与计算机工程系）
MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Qiyuan Tech（齐元科技）；Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（北京大学计算机科学学院多媒体信息处理实验室）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）
University of Science and Technology of China（中国科学技术大学）；CCCD Key Lab of Ministry of Culture and Tourism（文化和旅游部CCCD重点实验室）；National University of Singapore（新加坡国立大学）
Explainability is crucial for probing graph neural networks (GNNs), answering questions like "Why the GNN model makes a certain prediction?". Feature attribution is a prevalent technique of highlighting the explanatory subgraph in the input graph, which plausibly leads the GNN model to make its prediction. Various attribution methods exploit gradient-like or attention scores as the attributions of edges, then select the salient edges with top attribution scores as the explanation. However, most of these works make an untenable assumption - the selected edges are linearly independent - thus lea…
Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
Department of Computer Science, University of South Dakota（南达科他大学计算机科学系）；School of Information and Artificial Intelligence, Yangzhou University（扬州大学信息与人工智能学院）
We describe a formal approach based on graphical causal models to identify the "root causes" of the change in the probability distribution of variables. After factorizing the joint distribution into conditional distributions of each variable, given its parents (the "causal mechanisms"), we attribute the change to changes of these causal mechanisms. This attribution analysis accounts for the fact that mechanisms often change independently and sometimes only some of them change. Through simulations, we study the performance of our distribution change attribution method. We then present a real-wo…
