Papers Problem Decomposition
“Problem Decomposition” 태그가 달린 논문 54편 · 필터 해제
AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need
Large language model based multi-agent systems have demonstrated significant potential in social simulation and complex task resolution domains. However, current frameworks face critical challenges in system architecture…
GSM8KHumanEvalLarge Language ModelMath+1RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval
Scientific reasoning requires not only long-chain reasoning processes, but also knowledge of domain-specific terminologies and adaptation to updated findings. To deal with these challenges for scientific reasoning, we in…
Problem DecompositionRetrievalBeyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning
Reinforcement learning (RL) has become the dominant paradigm for endowing language models with advanced reasoning capabilities. Despite the substantial empirical gains demonstrated by RL-based training methods like GRPO,…
Mathematical ReasoningProblem Decompositionreinforcement-learningReinforcement Learning+1MAS-Zero: Designing Multi-Agent Systems with Zero Supervision
Multi-agent systems (MAS) leveraging the impressive capabilities of Large Language Models (LLMs) hold significant potential for tackling complex tasks. However, most current MAS depend on manually designed agent roles an…
MathProblem DecompositionMeta-Design Matters: A Self-Design Multi-Agent System
Multi-agent systems (MAS) leveraging the impressive capabilities of Large Language Models (LLMs) hold significant potential for tackling complex tasks. However, most current MAS depend on manually designed agent roles an…
MathProblem DecompositionInterpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation
Question Answering (QA) poses a challenging and critical problem, particularly in today's age of interactive dialogue systems such as ChatGPT, Perplexity, Microsoft Copilot, etc. where users demand both accuracy and tran…
Information RetrievalKnowledge DistillationMachine Reading ComprehensionProblem Decomposition+2Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition
Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extens…
GSM8KKnowledge DistillationMathProblem DecompositionTraining Large Language Models to Reason via EM Policy Gradient
Recently, foundation models such as OpenAI's O1 and O3, along with DeepSeek's R1, have demonstrated strong reasoning capacities and problem-solving skills acquired through large-scale reinforcement learning (RL), with wi…
GSM8KMathProblem Decompositionreinforcement-learning+2Availability of Perfect Decomposition in Statistical Linkage Learning for Unitation-based Function Concatenations
Statistical Linkage Learning (SLL) is a part of many state-of-the-art optimizers. The purpose of SLL is to discover variable interdependencies. It has been shown that the effectiveness of SLL-using optimizers is highly d…
Problem DecompositionLADDER: Self-Improving LLMs Through Recursive Problem Decomposition
We introduce LADDER (Learning through Autonomous Difficulty-Driven Example Recursion), a framework enabling LLMs to autonomously improve their problem-solving capabilities through self-guided learning. By recursively gen…
Problem Decompositionreinforcement-learningReinforcement LearningThe working principles of model-based GAs fall within the PAC framework: A mathematical theory of problem decomposition
The concepts of linkage, building blocks, and problem decomposition have long existed in the genetic algorithm (GA) field and have guided the development of model-based GAs for decades. However, their definitions are usu…
PAC learningProblem DecompositionStackelberg Game Based Performance Optimization in Digital Twin Assisted Federated Learning over NOMA Networks
Despite the advantage of preserving data privacy, federated learning (FL) still suffers from the straggler issue due to the limited computing resources of distributed clients and the unreliable wireless communication env…
Federated LearningProblem DecompositionTableTime: Reformulating Time Series Classification as Zero-Shot Table Understanding via Large Language Models
Large language models (LLMs) have demonstrated their effectiveness in multivariate time series classification (MTSC). Effective adaptation of LLMs for MTSC necessitates informative data representations. Existing LLM-base…
Problem DecompositionTime SeriesTime Series Classificationzero-shot-classification+1SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation
Large language models demonstrate exceptional performance in simple code generation tasks but still face challenges in tackling complex problems. These challenges may stem from insufficient reasoning and problem decompos…
Code GenerationDiversityProblem DecompositionUtilizing ChatGPT in a Data Structures and Algorithms Course: A Teaching Assistant's Perspective
Integrating large language models (LLMs) like ChatGPT into computer science education offers transformative potential for complex courses such as data structures and algorithms (DSA). This study examines ChatGPT as a sup…
Problem DecompositionNavigating the Nuances: A Fine-grained Evaluation of Vision-Language Navigation
This study presents a novel evaluation framework for the Vision-Language Navigation (VLN) task. It aims to diagnose current models for various instruction categories at a finer-grained level. The framework is structured …
Landmark RecognitionProblem DecompositionVision-Language NavigationMulti-service collaboration and composition of cloud manufacturing customized production based on problem decomposition
Cloud manufacturing system is a service-oriented and knowledge-based one, which can provide solutions for the large-scale customized production. The service resource allocation is the primary factor that restricts the pr…
Problem DecompositionService CompositionContext-aware Diversity Enhancement for Neural Multi-Objective Combinatorial Optimization
Multi-objective combinatorial optimization (MOCO) problems are prevalent in various real-world applications. Most existing neural MOCO methods rely on problem decomposition to transform an MOCO problem into a series of s…
Combinatorial OptimizationDiversityProblem DecompositionIndependent RL for Cooperative-Competitive Agents: A Mean-Field Perspective
We address in this paper Reinforcement Learning (RL) among agents that are grouped into teams such that there is cooperation within each team but general-sum (non-zero sum) competition across different teams. To develop …
Problem DecompositionReinforcement Learning (RL)A Composite Decomposition Method for Large-Scale Global Optimization
Cooperative co-evolution (CC) algorithms, based on the divide-and-conquer strategy, have emerged as the predominant approach to solving large-scale global optimization (LSGO) problems. The efficiency and accuracy of the …
global-optimizationProblem DecompositionVariable Detection