Image de couverture de livre

Dual-Scale World Models for LLM Agents Towards Hard-Exploration Problems

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kim, Minsoo, Hwang, Seung-won
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CoEx -- Co-evolving World-model and Exploration
par: Kim, Minsoo, et autres
Publié: (2025)

Disentangling Questions from Query Generation for Task-Adaptive Retrieval
par: Lee, Yoonsang, et autres
Publié: (2024)

Agent-as-Judge for Factual Summarization of Long Narratives
par: Jeong, Yeonseok, et autres
Publié: (2025)

Chaining Event Spans for Temporal Relation Grounding
par: Kim, Jongho, et autres
Publié: (2025)

Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models
par: Kim, Jongho, et autres
Publié: (2025)

CREFT: Sequential Multi-Agent LLM for Character Relation Extraction
par: Chun, Ye Eun, et autres
Publié: (2025)

Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents
par: Han, Hojae, et autres
Publié: (2026)

Intended Target Identification for Anomia Patients with Gradient-based Selective Augmentation
par: Kim, Jongho, et autres
Publié: (2025)

Benchmarking Testing in Automated Theorem Proving
par: Kim, Jongyoon, et autres
Publié: (2026)

Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding
par: Jung, Yeonjoon, et autres
Publié: (2024)

DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode
par: Han, Hojae, et autres
Publié: (2026)

HARP: Hesitation-Aware Reframing in Transformer Inference Pass
par: Storaï, Romain, et autres
Publié: (2024)

ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments
par: Han, Hojae, et autres
Publié: (2025)

SAFE: Stepwise Atomic Feedback for Error correction in Multi-hop Reasoning
par: Kwon, Daeyong, et autres
Publié: (2026)

Chain of Grounded Objectives: Bridging Process and Goal-oriented Prompting for Code Generation
par: Yeo, Sangyeop, et autres
Publié: (2025)

Inference Scaling for Bridging Retrieval and Augmented Generation
par: Lee, Youngwon, et autres
Publié: (2024)

Towards Lifelong Dialogue Agents via Timeline-based Memory Management
par: Ong, Kai Tzu-iunn, et autres
Publié: (2024)

ECoRAG: Evidentiality-guided Compression for Long Context RAG
par: Jeong, Yeonseok, et autres
Publié: (2025)

Relevance to Utility: Process-Supervised Rewrite for RAG
par: Kim, Jaeyoung, et autres
Publié: (2025)

ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models
par: Han, Hojae, et autres
Publié: (2024)

AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking
par: Yoon, Soyoung, et autres
Publié: (2025)

RoToR: Towards More Reliable Responses for Order-Invariant Inputs
par: Yoon, Soyoung, et autres
Publié: (2025)

PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation
par: Yoo, Jaeseok, et autres
Publié: (2024)

Relation-based Counterfactual Data Augmentation and Contrastive Learning for Robustifying Natural Language Inference Models
par: Yang, Heerin, et autres
Publié: (2024)

CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation
par: Lee, Youngwon, et autres
Publié: (2024)

Ever-Evolving Memory by Blending and Refining the Past
par: Kim, Seo Hyun, et autres
Publié: (2024)

DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning
par: Wan, Zhongwei, et autres
Publié: (2026)

R$^3$-SQL: Ranking Reward and Resampling for Text-to-SQL
par: Han, Hojae, et autres
Publié: (2026)

Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization
par: Lee, Janghwan, et autres
Publié: (2023)

Model-Based Data-Centric AI: Bridging the Divide Between Academic Ideals and Industrial Pragmatism
par: Park, Chanjun, et autres
Publié: (2024)

Agentic Verification for Ambiguous Query Disambiguation
par: Lee, Youngwon, et autres
Publié: (2025)

ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering
par: Wu, Ruofan, et autres
Publié: (2025)

Reinforcement World Model Learning for LLM-based Agents
par: Yu, Xiao, et autres
Publié: (2026)

POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
par: Qu, Yuxiao, et autres
Publié: (2026)

LASER: LLM Agent with State-Space Exploration for Web Navigation
par: Ma, Kaixin, et autres
Publié: (2023)

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
par: Kang, Minki, et autres
Publié: (2026)

LLM Agents at the Roundtable: A Multi-Perspective and Dialectical Reasoning Framework for Essay Scoring
par: Jang, Jinhee, et autres
Publié: (2025)

COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
par: Liu, Youwei, et autres
Publié: (2026)

$\textit{GeoHard}$: Towards Measuring Class-wise Hardness through Modelling Class Semantics
par: Cai, Fengyu, et autres
Publié: (2024)

DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents
par: Zhang, Junshuo, et autres
Publié: (2026)