paper-with-me

Workflow Discovery

1개 벤치마크 · 논문 4편 · 이 태스크의 논문 보기 →

Benchmarks

ABCD

결과 2개

Most implemented

Papers

AutoSynth: Automated Workflow Optimization for High-Quality Synthetic Dataset Generation via Monte Carlo Tree Search

2025-11-12 · Shuzhen Bi, Chang Song, Siyu Song, Jinze Lv 외 arxiv

Supervised fine-tuning (SFT) of large language models (LLMs) for specialized tasks requires high-quality datasets, but manual curation is prohibitively expensive. Synthetic data generation offers scalability, but its eff…

Synthetic Data GenerationPrompt EngineeringWorkflow Discovery

Opus: A Quantitative Framework for Workflow Evaluation

2025-11-06 · Alan Seroul, Théo Fagnoni, Inès Adnani, Dana O. Mohamed 외 arxiv

This paper introduces the Opus Workflow Evaluation Framework, a probabilistic-normative formulation for quantifying Workflow quality and efficiency. It integrates notions of correctness, reliability, and cost into a cohe…

Reinforcement LearningWorkflow Discovery

Leveraging Explicit Procedural Instructions for Data-Efficient Action Prediction

2023-06-06 · Julia White, Arushi Raghuvanshi, Yada Pruksachatkun

Task-oriented dialogues often require agents to enact complex, multi-step procedures in order to meet user requests. While large language models have found success automating these dialogues in constrained environments, …

Language ModelingLanguage ModellingLarge Language ModelMasked Language Modeling+3

Workflow Discovery from Dialogues in the Low Data Regime

2022-05-24 · Amine El Hattami, Stefania Raimondo, Issam Laradji, David Vazquez 외

Text-based dialogues are now widely used to solve real-world problems. In cases where solution strategies are already known, they can sometimes be codified into workflows and used to guide humans or artificial agents thr…

Workflow Discovery