The paper introduces a scalable framework that uses finetuned large language models (LLMs) to translate unstructured textual resources into structured event logs for process mining. By creating a new text-to-log dataset and finetuning LLMs on it, the authors demonstrate that the resulting models produce high‑fidelity event logs, outperforming few‑shot or zero‑shot prompting methods. This approach enables previously unused organizational data, such as incident tickets and manuals, to be incorporated into process mining workflows.
By Maximilian Seeth, Gabriel Marques Tavares, Daniel Schuster
arXiv:2608. 04697v1 Announce Type: new Abstract: Operational hazard analysis of aviation system operations must consider interactions among weather, ATC actions, airspace constraints, aircraft operations, and human factors - distinct from the functional hazard assessment applied at the aircraft-system level.
By Cristian Mascia, Roberto Pietrantuono, Daniel Rodriguez, Stefano Russo
Process mining (PM) provides a powerful framework for discovering and optimizing operational processes from event data. However, the efficacy of PM techniques is strictly predicated on the availabilit...
arXiv:2610.08364v1 Announce Type: new
Abstract: Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions fr...
By Toby D. Pilditch, Konstantinos Voudouris, Alexandra Abbas, Cozmin Ududec
The paper proposes a new framework for automated fault diagnostics in modern vehicles by treating diagnostic trouble codes (DTCs) as a high‑dimensional language. It introduces Transformer‑based models for predictive maintenance, scalable causal discovery methods, and a multi‑agent system that automatically generates Boolean error‑pattern rules. The approach aims to replace costly manual grouping of DTCs with scalable, data‑driven techniques.
By Hugo Math
Stack Trace-Based Crash Deduplication with Transformer Adaptation introduces dedupT, a transformer‑based method that models entire stack traces instead of isolated frames. The approach first fine‑tunes a pretrained language model on stack traces and then trains a fully‑connected network to rank duplicate crashes. Experiments on four public datasets show dedupT improves Mean Reciprocal Rank by over 15% versus the best deep‑learning baseline and up to 10% over traditional methods, while also achieving higher ROC‑AUC for unique crash detection.
By Md Afif Al Mamun, Gias Uddin, Lan Xia, Longyu Zhang
arXiv:2609.33676v2 Announce Type: replace
Abstract: LLM agents increasingly take consequential actions through interactions with users, policies, and external tools. Auditing these agents requires au...
By Yifan Liu, Praveen Venkateswaran, Abdulhamid Adebayo, Dong Wang
The paper introduces Continual Search, an iterative framework that guides large language models to persistently search for diagnostic evidence in long AI agent execution logs, addressing the limitations of one-shot judgments. Evaluated on four existing RCA benchmarks and a new large-scale dataset called MegaRCA-Mix, Continual Search consistently boosts attribution performance, achieving a 40% F1 improvement for GPT‑5.5 on MegaRCA‑Mix. The results show that effective search can outweigh raw model scale, enabling lower-tier models to outperform higher-tier ones in root‑cause attribution tasks.
By Harsh Raj, David Lee, Anas Mahmoud, Renxiong Wang, Razvan-Gabriel Dumitru, Chenguang Wang, Tong Zhao, Yunzhong He, Darvin Yi, Vipul Gupta
Event analysis is an essential and fundamental direction of information extraction, involving various event-centric tasks at different granularity of documents. While large language models (LLMs) have preliminarily achieved promising performance in part of these tasks individually, their capability in event analysis still lacks comprehensive understanding due to restricted document granularity, task designs, and data source of existing benchmarks.
AuditKIT is a source‑available evaluation library that unifies benchmark accuracy, judge‑based assessment, runtime performance, tool‑use behavior, and retrieval quality into a single result representation. It offers direction‑aware metric contracts, configuration fingerprints, and extensible metrics and backends, while providing turn‑aware tool‑call matching and distinguishing verified task outcomes from trajectory‑level diagnostics. Seven case studies demonstrate how answer extraction, runtime behavior, and metric selection can alter evaluation outcomes across model comparison, serving runtimes, retrieval, tool calling, and interoperability.
By Shreeyans Arora, Utsav Avaiya, Zera Lyngkhoi, Hem Gosalia, Ram Mohan Rao Kadiyala, Vinay Kumar Sankarapu, Pratinav Seth
arXiv:2606. 08376v1 Announce Type: cross Abstract: As artificial intelligence (AI) systems are increasingly deployed across socially consequential domains, reports of AI-related harms and failures have grown in frequency and diversity.
By Leihan Zhang, Wecheng Ye, Xianlong Ma, Haochuan Liu, Yang Li, Qianyu Zhang, Jinliang Chen, Qiang Yan
arXiv:2607. 08093v1 Announce Type: new Abstract: Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use.
By Andrej Leban, Yuekai Sun