Copertina

A Training-free LLM Framework with Interaction between Contextually Related Subtasks in Solving Complex Tasks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Hongjia, Li, Jinlong
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Enhancing Complex Causality Extraction via Improved Subtask Interaction and Knowledge Fusion
di: Gao, Jinglong, et al.
Pubblicazione: (2024)

Lag-Relative Sparse Attention In Long Context Training
di: Liang, Manlai, et al.
Pubblicazione: (2025)

Neural Bandit Based Optimal LLM Selection for a Pipeline of Subtasks
di: Atalar, Baran, et al.
Pubblicazione: (2025)

ELYADATA & LIA at NADI 2025: ASR and ADI Subtasks
di: Elleuch, Haroun, et al.
Pubblicazione: (2025)

On the Paradoxical Interference between Instruction-Following and Task Solving
di: Qi, Yunjia, et al.
Pubblicazione: (2026)

Decoupling Task-Solving and Output Formatting in LLM Generation
di: Deng, Haikang, et al.
Pubblicazione: (2025)

TeamLLM: A Human-Like Team-Oriented Collaboration Framework for Multi-Step Contextualized Tasks
di: Wang, Xiangyu, et al.
Pubblicazione: (2026)

Multi-LLM Collaborative Search for Complex Problem Solving
di: Yang, Sen, et al.
Pubblicazione: (2025)

Assessing Open-Source Large Language Models on Argumentation Mining Subtasks
di: Abkenar, Mohammad Yeghaneh, et al.
Pubblicazione: (2024)

Characterizing Knowledge Graph Tasks in LLM Benchmarks Using Cognitive Complexity Frameworks
di: Todorovikj, Sara, et al.
Pubblicazione: (2025)

Large Language Model-based Human-Agent Collaboration for Complex Task Solving
di: Feng, Xueyang, et al.
Pubblicazione: (2024)

Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs
di: Yang, Zhipeng, et al.
Pubblicazione: (2025)

One LLM to Train Them All: Multi-Task Learning Framework for Fact-Checking
di: Larsson, Malin Astrid, et al.
Pubblicazione: (2026)

LLM for Complex Reasoning Task: An Exploratory Study in Fermi Problems
di: Liu, Zishuo, et al.
Pubblicazione: (2025)

A Survey on Complex Tasks for Goal-Directed Interactive Agents
di: Hartmann, Mareike, et al.
Pubblicazione: (2024)

A Training-free LLM-based Approach to General Chinese Character Error Correction
di: Zhou, Houquan, et al.
Pubblicazione: (2025)

Fast-Slow-Thinking: Complex Task Solving with Large Language Models
di: Sun, Yiliu, et al.
Pubblicazione: (2025)

G-SciEdBERT: A Contextualized LLM for Science Assessment Tasks in German
di: Latif, Ehsan, et al.
Pubblicazione: (2024)

KLong: Training LLM Agent for Extremely Long-horizon Tasks
di: Liu, Yue, et al.
Pubblicazione: (2026)

From Task Solving to Robust Real-World Adaptation in LLM Agents
di: Pezeshkpour, Pouya, et al.
Pubblicazione: (2026)

Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
di: Wu, Chengyue, et al.
Pubblicazione: (2025)

Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation
di: Liang, Chen, et al.
Pubblicazione: (2024)

RCStat: A Statistical Framework for using Relative Contextualization in Transformers
di: Mahapatra, Debabrata, et al.
Pubblicazione: (2025)

Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Tasks
di: Wang, Yihan, et al.
Pubblicazione: (2025)

Transformer Enhanced Relation Classification: A Comparative Analysis of Contextuality, Data Efficiency and Sequence Complexity
di: Jing, Bowen, et al.
Pubblicazione: (2025)

Embracing Ambiguity: Improving Similarity-oriented Tasks with Contextual Synonym Knowledge
di: Li, Yangning, et al.
Pubblicazione: (2022)

A Hybrid GA LLM Framework for Structured Task Optimization
di: Shum, William, et al.
Pubblicazione: (2025)

SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning
di: Ma, Zexiong, et al.
Pubblicazione: (2025)

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

StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
di: Wu, Yiran, et al.
Pubblicazione: (2024)

XL3M: A Training-free Framework for LLM Length Extension Based on Segment-wise Inference
di: Wang, Shengnan, et al.
Pubblicazione: (2024)

ContextualLVLM-Agent: A Holistic Framework for Multi-Turn Visually-Grounded Dialogue and Complex Instruction Following
di: Han, Seungmin, et al.
Pubblicazione: (2025)

CRAB-Bench: Evaluating LLM Agents under Complex Task Dependencies and Human-aligned User Simulation
di: Wang, Danqing, et al.
Pubblicazione: (2026)

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

CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLM
di: Lee, Juntae, et al.
Pubblicazione: (2025)

Training-free LLM-generated Text Detection by Mining Token Probability Sequences
di: Xu, Yihuai, et al.
Pubblicazione: (2024)

IGC: Integrating a Gated Calculator into an LLM to Solve Arithmetic Tasks Reliably and Efficiently
di: Dietz, Florian, et al.
Pubblicazione: (2025)

PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving
di: Parmar, Mihir, et al.
Pubblicazione: (2025)

PROMISE: A Framework for Developing Complex Conversational Interactions (Technical Report)
di: Wu, Wenyuan, et al.
Pubblicazione: (2023)

Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models
di: Wang, Xiaolong, et al.
Pubblicazione: (2024)