paper-with-me

Papers Problem Decomposition

“Problem Decomposition” 태그가 달린 논문 54편 · 필터 해제

AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need

2025-06-18 · Zhouhong Gu, Xiaoxuan Zhu, Yin Cai, Hao Shen 외

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+1

RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval

2025-06-10 · Minhae Oh, Jeonghye Kim, Nakyung Lee, Donggeon Seo 외

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 DecompositionRetrieval

Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning

2025-06-05 · Jiayu Wang, Yifei Ming, Zixuan Ke, Caiming Xiong 외

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+1

MAS-Zero: Designing Multi-Agent Systems with Zero Supervision

2025-05-26 · arXiv 2025 5 · Zixuan Ke, Austin Xu, Yifei Ming, Xuan-Phi Nguyen 외

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 Decomposition

Meta-Design Matters: A Self-Design Multi-Agent System

2025-05-21 · Zixuan Ke, Austin Xu, Yifei Ming, Xuan-Phi Nguyen 외

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 Decomposition

Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation

2025-05-20 · Siddhant Bhambri, Upasana Biswas, Subbarao Kambhampati

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+2

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition

2025-04-29 · Tyler McDonald, Ali Emami

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 Decomposition

Training Large Language Models to Reason via EM Policy Gradient

2025-04-24 · Tianbing Xu

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+2

Availability of Perfect Decomposition in Statistical Linkage Learning for Unitation-based Function Concatenations

2025-03-18 · Michal Prusik, Bartosz Frej, Michal W. Przewozniczek

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 Decomposition

LADDER: Self-Improving LLMs Through Recursive Problem Decomposition

2025-03-02 · Toby Simonds, Akira Yoshiyama

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 Learning

The working principles of model-based GAs fall within the PAC framework: A mathematical theory of problem decomposition

2025-01-18 · Tian-Li Yu, Chi-Hsien Chang, Ying-ping Chen

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 Decomposition

Stackelberg Game Based Performance Optimization in Digital Twin Assisted Federated Learning over NOMA Networks

2025-01-03 · Bibo Wu, Fang Fang, Xianbin Wang

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 Decomposition

TableTime: Reformulating Time Series Classification as Zero-Shot Table Understanding via Large Language Models

2024-11-24 · Jiahao Wang, Mingyue Cheng, Qingyang Mao, Qi Liu 외

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+1

SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation

2024-11-17 · Bin Xu, Yiguan Lin, Yinghao Li, Yang Gao

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 Decomposition

Utilizing ChatGPT in a Data Structures and Algorithms Course: A Teaching Assistant's Perspective

2024-10-11 · Pooriya Jamie, Reyhaneh Hajihashemi, Sharareh Alipour

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 Decomposition

Navigating the Nuances: A Fine-grained Evaluation of Vision-Language Navigation

2024-09-25 · Zehao Wang, Minye Wu, Yixin Cao, Yubo Ma 외

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 Navigation

Multi-service collaboration and composition of cloud manufacturing customized production based on problem decomposition

2024-06-28 · Hao Yue, Yingtao Wu, Min Wang, Hesuan Hu 외

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 Composition

Context-aware Diversity Enhancement for Neural Multi-Objective Combinatorial Optimization

2024-05-14 · Yongfan Lu, Zixiang Di, Bingdong Li, Shengcai Liu 외

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 Decomposition

Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective

2024-03-17 · Muhammad Aneeq uz Zaman, Alec Koppel, Mathieu Laurière, Tamer Başar

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

2024-03-02 · Maojiang Tian, Minyang Chen, Wei Du, Yang Tang 외

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
1–20 / 54 다음 →