Imagen de Portada

StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wu, Yiran, Yue, Tianwei, Zhang, Shaokun, Wang, Chi, Wu, Qingyun
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Offline Training of Language Model Agents with Functions as Learnable Weights
por: Zhang, Shaokun, et al.
Publicado: (2024)

Towards better Human-Agent Alignment: Assessing Task Utility in LLM-Powered Applications
por: Arabzadeh, Negar, et al.
Publicado: (2024)

HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows
por: Yao, Wenlin, et al.
Publicado: (2024)

EcoAct: Economic Agent Determines When to Register What Action
por: Zhang, Shaokun, et al.
Publicado: (2024)

WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models
por: Fan, Shengda, et al.
Publicado: (2024)

Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation
por: Niu, Cheng, et al.
Publicado: (2024)

BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
por: Ding, Dujian, et al.
Publicado: (2025)

Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning
por: Zhang, Shaokun, et al.
Publicado: (2025)

Explain Less, Understand More: Jargon Detection via Personalized Parameter-Efficient Fine-tuning
por: Wu, Bohao, et al.
Publicado: (2025)

LLM Factoscope: Uncovering LLMs' Factual Discernment through Inner States Analysis
por: He, Jinwen, et al.
Publicado: (2023)

Enhancing Text Annotation through Rationale-Driven Collaborative Few-Shot Prompting
por: Wu, Jianfei, et al.
Publicado: (2024)

Deep Literature Survey Automation with an Iterative Workflow
por: Zhang, Hongbo, et al.
Publicado: (2025)

Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models
por: Su, Weihang, et al.
Publicado: (2024)

Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration
por: Wang, Zhenhailong, et al.
Publicado: (2023)

Assessing and Verifying Task Utility in LLM-Powered Applications
por: Arabzadeh, Negar, et al.
Publicado: (2024)

Absolute Zero: Reinforced Self-play Reasoning with Zero Data
por: Zhao, Andrew, et al.
Publicado: (2025)

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
por: Zeng, Yifan, et al.
Publicado: (2026)

LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking
por: Zeng, Yifan, et al.
Publicado: (2024)

MAC-Tuning: LLM Multi-Compositional Problem Reasoning with Enhanced Knowledge Boundary Awareness
por: Huang, Junsheng, et al.
Publicado: (2025)

EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
por: Wu, Rong, et al.
Publicado: (2025)

AnyTaskTune: Advanced Domain-Specific Solutions through Task-Fine-Tuning
por: Cui, Jiaxi, et al.
Publicado: (2024)

AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization
por: Gu, Haoran, et al.
Publicado: (2026)

Perspective Transition of Large Language Models for Solving Subjective Tasks
por: Wang, Xiaolong, et al.
Publicado: (2025)

Anagent For Enhancing Scientific Table & Figure Analysis
por: Guo, Xuehang, et al.
Publicado: (2026)

FlowMind: Automatic Workflow Generation with LLMs
por: Zeng, Zhen, et al.
Publicado: (2024)

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
por: Zhang, Shaokun, et al.
Publicado: (2025)

MathChat: Converse to Tackle Challenging Math Problems with LLM Agents
por: Wu, Yiran, et al.
Publicado: (2023)

Speak & Spell: LLM-Driven Controllable Phonetic Error Augmentation for Robust Dialogue State Tracking
por: Lee, Jihyun, et al.
Publicado: (2024)

RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving
por: Ding, Zepeng, et al.
Publicado: (2025)

On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows
por: Wang, Xinglin, et al.
Publicado: (2026)

What are Models Thinking about? Understanding Large Language Model Hallucinations "Psychology" through Model Inner State Analysis
por: Wang, Peiran, et al.
Publicado: (2025)

Solving a Million-Step LLM Task with Zero Errors
por: Meyerson, Elliot, et al.
Publicado: (2025)

SWAA: Sliding Window Attention Adaptation for Efficient and Quality Preserving Long Context Processing
por: Yu, Yijiong, et al.
Publicado: (2025)

StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking
por: Rozanov, Nikolai, et al.
Publicado: (2024)

Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement
por: Cao, Maosong, et al.
Publicado: (2025)

MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion
por: Pei, Qizhi, et al.
Publicado: (2025)

ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
por: Wu, Yiran, et al.
Publicado: (2025)

MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows
por: Zhang, Xingjian, et al.
Publicado: (2024)

An LLM + ASP Workflow for Joint Entity-Relation Extraction
por: Tran, Trang, et al.
Publicado: (2025)

The LLM Fallacy: Misattribution in AI-Assisted Cognitive Workflows
por: Kim, Hyunwoo, et al.
Publicado: (2026)