English
Related papers

Related papers: Runtime-Structured Task Decomposition for Agentic …

200 papers

Scientific workflow systems automate execution -- scheduling, fault tolerance, resource management -- but not the semantic translation that precedes it. Scientists still manually convert research questions into workflow specifications, a…

Artificial Intelligence · Computer Science 2026-04-24 Bartosz Balis , Michal Orzechowski , Piotr Kica , Michal Dygas , Michal Kuszewski

Ad hoc dataset search requires matching underspecified natural-language queries against sparse, heterogeneous metadata records, a task where typical lexical or dense retrieval alone falls short. We reposition dataset search as a…

Information Retrieval · Computer Science 2026-04-21 Riccardo Terrenzi , Phongsakon Mark Konrad , Tim Lukas Adam , Serkan Ayvaz

Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based reasoning. However, debugging these models remains a persistent challenge due to their…

Modernizing legacy COBOL systems remains difficult due to scarce expertise, large and long-lived codebases, and strict correctness requirements. Recent large language model (LLM)-based modernization systems increasingly rely on agentic…

Software Engineering · Computer Science 2026-05-12 Naing Oo Lwin , Rajesh Kumar

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…

Software Engineering · Computer Science 2026-04-06 Tural Mehtiyev , Wesley Assunção

Fraud detection and anti-money-laundering (AML) compliance are high-value domains for large language models (LLMs), but their serving requirements differ sharply from generic chat workloads. Compliance prompts are often prefix-heavy,…

Artificial Intelligence · Computer Science 2026-05-13 Prathamesh Vasudeo Naik , Naresh Dintakurthi , Yue Wang

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, but optimizing LLM-based agentic systems remains challenging due to the vast search space of agent configurations, prompting strategies, and…

Machine Learning · Computer Science 2026-03-02 Patara Trirat , Wonyong Jeong , Sung Ju Hwang

The rapid advancement of large language models (LLMs) demands robust, unbiased, and scalable evaluation methods. However, human annotations are costly to scale, model-based evaluations are susceptible to stylistic biases, and…

Debugging consumes a substantial portion of the software development lifecycle, yet the effectiveness of Large Language Models(LLMs) in this task is not well understood. Competitive programming offers a rich benchmark for such evaluation,…

Software Engineering · Computer Science 2026-03-23 Nabiha Parvez , Tanvin Sarkar Pallab , Mia Mohammad Imran , Tarannum Shaila Zaman

Large language models (LLMs) are increasingly being used to generate health text from structured records such as wearable time series, biomarkers, vitals, and care-management logs. For recurring health outputs, fluency is not enough:…

Artificial Intelligence · Computer Science 2026-05-29 Kai-Chen Cheng , Haejun Han , David Q. Sun

Databricks job orchestration systems (e.g., LeJOT) reduce cloud costs by selecting low-priced compute configurations while meeting latency and dependency constraints. Accurate execution-time prediction under heterogeneous instance types and…

Machine Learning · Computer Science 2026-03-10 Lizhi Ma , Yi-Xiang Hu , Yihui Ren , Feng Wu , Xiang-Yang Li

Security analysts are overwhelmed by the volume of alerts and the low context provided by many detection systems. Early-stage investigations typically require manual correlation across multiple log sources, a task that is usually…

Cryptography and Security · Computer Science 2026-04-29 Even Eilertsen , Vasileios Mavroeidis , Gudmund Grov

The rapid evolution of Large Language Models (LLM) and subsequent Agentic AI technologies requires systematic architectural guidance for building sophisticated, production-grade systems. This paper presents an approach for architecting such…

Artificial Intelligence · Computer Science 2026-05-26 Zoran Milosevic , Fethi Rabhi

Algorithmic reasoning refers to the ability to understand the complex patterns behind the problem and decompose them into a sequence of reasoning steps towards the solution. Such nature of algorithmic reasoning makes it a challenge for…

Large language models can consult information that fixed static analyzers cannot, such as documentation, current security advisories, version-specific metadata, and informal API contracts. This makes LLMs a compelling option for program…

Software Engineering · Computer Science 2026-05-14 Jacqueline L. Mitchell , Chao Wang

We introduce TDFlow, a novel test-driven agentic workflow that frames repository-scale software engineering as a test-resolution task, specifically designed to solve human-written tests. Given a set of tests, TDFlow repeatedly proposes,…

Software Engineering · Computer Science 2026-01-23 Kevin Han , Siddharth Maddikayala , Tim Knappe , Om Patel , Austen Liao , Amir Barati Farimani

Engineering analysis automation in product development relies on rigid interfaces between tools, data formats and documented processes. When these interfaces change, as they routinely do as the product evolves in the engineering ecosystem,…

Software Engineering · Computer Science 2026-03-18 Alejandro Pradas-Gomez , Arindam Brahma , Ola Isaksson

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…

Artificial Intelligence · Computer Science 2025-07-16 Junde Wu , Jiayuan Zhu , Yuyuan Liu , Min Xu , Yueming Jin

In programming education, Debugging and Teaching (DT) task is a common scenario where students receive assistance in correcting their erroneous code. The task involves multiple inputs, including erroneous code, error messages, reference…

Software Engineering · Computer Science 2025-10-14 Lingyue Fu , Haowei Yuan , Datong Chen , Xinyi Dai , Qingyao Li , Weinan Zhang , Weiwen Liu , Yong Yu

We introduce SLR, an end-to-end framework for systematic evaluation and training of Large Language Models (LLMs) via Scalable Logical Reasoning. Given a user's task specification, SLR automatically synthesizes (i) an instruction prompt for…