Review

[논문리뷰] EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs

arXiv에 게시된 'EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Reasoning #Model Calibration #Epistemic Uncertainty #Self-Training #Supervised Fine-tuning #Confidence-Informed Self-Consistency #Model Collapse

2026년 1월 13일

[논문리뷰] End-to-End Video Character Replacement without Structural Guidance

arXiv에 게시된 'End-to-End Video Character Replacement without Structural Guidance' 논문에 대한 자세한 리뷰입니다.

#Review #Video Character Replacement #Diffusion Models #In-Context Learning #Reinforcement Learning #Structural Guidance #Video Editing #Data Generation Pipeline

2026년 1월 13일

[논문리뷰] ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking

arXiv에 게시된 'ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #LLM Agents #Open-Ended Tasks #Relative Ranking #Tournament-based Ranking #Discriminative Collapse #Reward Modeling #Benchmarks

2026년 1월 13일

[논문리뷰] Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization

arXiv에 게시된 'Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Visualization #Reinforcement Learning #Multi-Objective Optimization #GRPO #Multimodal Feedback #LLMs #Code Generation

2026년 1월 13일

[논문리뷰] X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests

Jane Luo이 arXiv에 게시한 'X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests' 논문에 대한 자세한 리뷰입니다.

#Review #Competitive Programming #Code LLMs #Synthetic Data Generation #Supervised Fine-tuning (SFT)#Reinforcement Learning (RL)#Dual Verification #Scaling Laws #SynthSmith

2026년 1월 12일

[논문리뷰] What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models

arXiv에 게시된 'What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Models #Under-specified Queries #Multimodal Benchmark #HAERAE-Vision #Query Explicitation #Retrieval Augmentation #Cultural Knowledge #Korean QA

2026년 1월 12일

[논문리뷰] Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

Shuo Zhang이 arXiv에 게시한 'Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Video Question Answering #Open-domain Search #Multimodal LLMs #Agentic AI #Benchmark #Video Understanding #Multi-hop Reasoning

2026년 1월 12일

[논문리뷰] TourPlanner: A Competitive Consensus Framework with Constraint-Gated Reinforcement Learning for Travel Planning

Hao Wang이 arXiv에 게시한 'TourPlanner: A Competitive Consensus Framework with Constraint-Gated Reinforcement Learning for Travel Planning' 논문에 대한 자세한 리뷰입니다.

#Review #Travel Planning #LLM Agents #Reinforcement Learning #Multi-path Reasoning #Constraint Satisfaction #POI Optimization #Chain-of-Thought

2026년 1월 12일

[논문리뷰] Structured Episodic Event Memory

arXiv에 게시된 'Structured Episodic Event Memory' 논문에 대한 자세한 리뷰입니다.

#Review #LLMs #RAG #Episodic Memory #Graph Memory #Memory Architecture #Narrative Coherence #Long-term Reasoning #Event Frames

2026년 1월 12일

[논문리뷰] PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning

arXiv에 게시된 'PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #PaCoRe #Test-Time Compute Scaling #LLMs #Parallel Reasoning #Reinforcement Learning #Reasoning Synthesis #Message Passing #Mathematical Reasoning

2026년 1월 12일

[논문리뷰] OpenTinker: Separating Concerns in Agentic Reinforcement Learning

Jiaxuan You이 arXiv에 게시한 'OpenTinker: Separating Concerns in Agentic Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #LLM Agents #Multi-Agent Systems #System Architecture #Separation of Concerns #RLaaS #Distributed Training #Agent Protocol Coordination

2026년 1월 12일

[논문리뷰] On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation

Ju-Chieh Chou이 arXiv에 게시한 'On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation' 논문에 대한 자세한 리뷰입니다.

#Review #Spoken Language Models #Evaluation Metrics #Perplexity #Mean Opinion Score #Likelihood-based Evaluation #Model-as-a-Judge #Acoustic Consistency #Speech Generation

2026년 1월 12일

[논문리뷰] OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent

arXiv에 게시된 'OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent' 논문에 대한 자세한 리뷰입니다.

#Review #Computer-Using Agent (CUA)#Multi-Agent Framework #Long-horizon Tasks #Memory Management #Multimodal Retrieval #Reflection #Generalization

2026년 1월 12일

[논문리뷰] MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era

Fan Zhou이 arXiv에 게시한 'MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic AI #Distributed Orchestration #Scalability #Cloud-Native #Reinforcement Learning #Software Engineering Agents #Resource Management

2026년 1월 12일

[논문리뷰] MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

arXiv에 게시된 'MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head' 논문에 대한 자세한 리뷰입니다.

#Review #Linear Attention #Multi-Head Attention #Transformer #Global Context Collapse #Representational Diversity #Image Generation #NLP #Video Generation

2026년 1월 12일

[논문리뷰] Lost in the Noise: How Reasoning Models Fail with Contextual Distractors

arXiv에 게시된 'Lost in the Noise: How Reasoning Models Fail with Contextual Distractors' 논문에 대한 자세한 리뷰입니다.

#Review #Robustness #Contextual Distractors #RAG #Reasoning Models #Alignment #Tool Use #NoisyBench #Rationale-Aware Reward #Inverse Scaling

2026년 1월 12일

[논문리뷰] GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts

arXiv에 게시된 'GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts' 논문에 대한 자세한 리뷰입니다.

#Review #Collaborative Inference #Large Reasoning Models (LRMs)#Inference Latency #Step-wise Routing #Initial Token Entropy #Dynamic Routing #Computational Efficiency

2026년 1월 12일

[논문리뷰] ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration

arXiv에 게시된 'ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models (LLMs)#Tool-Integrated Reasoning (TIR)#Agent Behavior Calibration #Reinforcement Learning (RL)#Self-Evolving Data Flywheel #Action Space Exploration #Behavioral Efficiency

2026년 1월 12일

[논문리뷰] DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving

arXiv에 게시된 'DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving' 논문에 대한 자세한 리뷰입니다.

#Review #Generative World Models #Autonomous Driving #Video Generation #Benchmark #Evaluation Metrics #Trajectory Prediction #Temporal Consistency #Data Diversity

2026년 1월 12일

[논문리뷰] Dr. Zero: Self-Evolving Search Agents without Training Data

Shaoliang Nie이 arXiv에 게시한 'Dr. Zero: Self-Evolving Search Agents without Training Data' 논문에 대한 자세한 리뷰입니다.

#Review #Self-Evolution #Search Agents #Large Language Models (LLMs)#Data-Free Learning #Reinforcement Learning (RL)#Hop-Grouped Relative Policy Optimization (HRPO)#Question Answering #Multi-hop Reasoning

2026년 1월 12일