English
Related papers

Related papers: Failure-Driven Workflow Refinement

200 papers

Model merging unifies independently fine-tuned LLMs from the same base, enabling reuse and integration of parallel development efforts without retraining. However, in practice we observe that merging does not always succeed: certain…

Artificial Intelligence · Computer Science 2026-03-11 Yuan Cao , Dezhi Ran , Yuzhe Guo , Mengzhou Wu , Simin Chen , Linyi Li , Wei Yang , Tao Xie

We present a novel local improvement scheme for the perfectly balanced graph partitioning problem. This scheme encodes local searches that are not restricted to a balance constraint into a model allowing us to find combinations of these…

Data Structures and Algorithms · Computer Science 2012-10-02 Peter Sanders , Christian Schulz

Graphs are a widely used paradigm for representing non-Euclidean data, with applications ranging from social network analysis to biomolecular prediction. While graph learning has achieved remarkable progress, real-world graph data presents…

A truly effective diagnostic system provides system engineers with valuable insights into the behavior of their machines, leveraging a rich body of (often tacit) expertise. Much of this expertise typically resides in written documentation…

Other Computer Science · Computer Science 2025-09-03 Manzi Aimé Ntagengerwa , Georgiana Caltais , Mariëlle Stoelinga

Fault-tolerant distributed algorithms are central for building reliable spatially distributed systems. Unfortunately, the lack of a canonical precise framework for fault-tolerant algorithms is an obstacle for both verification and…

Formal Languages and Automata Theory · Computer Science 2012-10-16 Annu John , Igor Konnov , Ulrich Schmid , Helmut Veith , Josef Widder

In an edge-cloud system, mobile devices can offload their computation intensive tasks to an edge or cloud server to guarantee the quality of service or satisfy task deadline requirements. However, it is challenging to determine where tasks…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-03-08 Chuanchao Gao , Aryaman Shaan , Arvind Easwaran

We propose a new, training-free method, Graph Reasoning via Retrieval Augmented Framework (GRRAF), that harnesses retrieval-augmented generation (RAG) alongside the code-generation capabilities of large language models (LLMs) to address a…

Artificial Intelligence · Computer Science 2025-09-17 Hanqing Li , Kiran Sheena Jyothi , Henry Liang , Sharika Mahadevan , Diego Klabjan

Large Language Models (LLMs) typically rely on Supervised Fine-Tuning (SFT) to specialize in downstream tasks, with the Cross Entropy (CE) loss being the de facto choice. However, CE maximizes the likelihood of observed data without…

Machine Learning · Computer Science 2025-04-08 Ziniu Li , Congliang Chen , Tian Xu , Zeyu Qin , Jiancong Xiao , Zhi-Quan Luo , Ruoyu Sun

Large Language Models (LLMs) have demonstrated strong capabilities in various natural language processing tasks; however, their application to graph-related problems remains limited, primarily due to scalability constraints and the absence…

Machine Learning · Computer Science 2025-05-08 Hyun Lee , Chris Yi , Maminur Islam , B. D. S. Aritra

The growing penetration of distributed energy resources (DERs) is leading to continually changing operating conditions, which need to be managed efficiently by distribution grid operators. The intermittent nature of DERs such as solar…

Systems and Control · Electrical Eng. & Systems 2022-07-21 Kshitij Girigoudar , Ashley M. Hou , Line A. Roald

We introduce a novel semi-supervised Graph Counterfactual Explainer (GCE) methodology, Dynamic GRAph Counterfactual Explainer (DyGRACE). It leverages initial knowledge about the data distribution to search for valid counterfactuals while…

Machine Learning · Computer Science 2023-08-07 Bardh Prenkaj , Mario Villaizan-Vallelado , Tobias Leemann , Gjergji Kasneci

Systematic failures of computer vision models on subsets with coherent visual patterns, known as error slices, pose a critical challenge for robust model evaluation. Existing slice discovery methods are primarily developed for image…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Wei Zhang , Chaoqun Wang , Zixuan Guan , Sam Kao , Pengfei Zhao , Peng Wu , Sifeng He

Capturing the workload of a database and replaying this workload for a new version of the database can be an effective approach for regression testing. However, false positive errors caused by many factors such as data privacy limitations,…

Machine Learning · Computer Science 2024-12-19 Neetha Jambigi , Joshua Hammesfahr , Moritz Mueller , Thomas Bach , Michael Felderer

Large language model (LLM)-enhanced recommendation models inject LLM representations into backbone recommenders to exploit rich item text without inference-time LLM cost. However, we find that existing LLM-enhanced methods significantly…

Information Retrieval · Computer Science 2026-04-23 Zhangchi Zhu , Wei Zhang

Modern deep learning systems require huge data sets to achieve impressive performance, but there is little guidance on how much or what kind of data to collect. Over-collecting data incurs unnecessary present costs, while under-collecting…

Machine Learning · Computer Science 2022-10-05 Rafid Mahmood , James Lucas , Jose M. Alvarez , Sanja Fidler , Marc T. Law

Unbalanced data arises in many learning tasks such as clustering of multi-class data, hierarchical divisive clustering and semisupervised learning. Graph-based approaches are popular tools for these problems. Graph construction is an…

Machine Learning · Statistics 2011-12-13 Jing Qian , Venkatesh Saligrama , Manqi Zhao

LLM systems must make control decisions in addition to generating outputs: whether to answer, clarify, retrieve, call tools, repair, or escalate. In many current architectures, these decisions remain implicit within generation, entangling…

Artificial Intelligence · Computer Science 2026-04-02 Wei Sun

We present Logics-STEM, a state-of-the-art reasoning model fine-tuned on Logics-STEM-SFT-Dataset, a high-quality and diverse dataset at 10M scale that represents one of the largest-scale open-source long chain-of-thought corpora.…

The integration of Formal Verification tools with Large Language Models (LLMs) offers a path to scale software verification beyond manual workflows. However, current methods remain unreliable: without a solid theoretical footing, the…

Artificial Intelligence · Computer Science 2025-12-18 PIerre Dantas , Lucas Cordeiro , Youcheng Sun , Waldir Junior

The reliability of cloud platforms is of significant relevance because society increasingly relies on complex software systems running on the cloud. To improve it, cloud providers are automating various maintenance tasks, with failure…

Software Engineering · Computer Science 2022-04-07 Jasmin Bogatinovski , Sasho Nedelkoski , Li Wu , Jorge Cardoso , Odej Kao