Review

[논문리뷰] Code2World: A GUI World Model via Renderable Code Generation

arXiv에 게시된 'Code2World: A GUI World Model via Renderable Code Generation' 논문에 대한 자세한 리뷰입니다.

#Review #GUI World Model #Renderable Code Generation #Vision-Language Model #Reinforcement Learning #HTML Synthesis #UI Prediction #GUI Agents

2026년 2월 10일

[논문리뷰] Chain of Mindset: Reasoning with Adaptive Cognitive Modes

arXiv에 게시된 'Chain of Mindset: Reasoning with Adaptive Cognitive Modes' 논문에 대한 자세한 리뷰입니다.

#Review #Adaptive Reasoning #Cognitive Modes #Large Language Models (LLMs)#Agentic AI #Multimodal Reasoning #Mindset Orchestration #Contextual Filtering #Training-free Framework

2026년 2월 10일

[논문리뷰] BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation

Xiaoyu Chen이 arXiv에 게시한 'BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Long-horizon manipulation #Embodied AI #Vision-Language-Action (VLA)#Interleaved planning #Visual forecasting #Residual Flow Guidance #Multimodal learning

2026년 2월 10일

[논문리뷰] Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

arXiv에 게시된 'Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic AI #Reinforcement Learning #Synthetic Environments #Tool-Use Agents #World Model #Database-Backed Simulation #LLM-powered Agents

2026년 2월 10일

[논문리뷰] Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling

arXiv에 게시된 'Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Agentic AI #Multi-turn Interaction #High-Fidelity #Native Resolution #LLM #Context Folding #Layer Decomposition

2026년 2월 10일

[논문리뷰] WorldCompass: Reinforcement Learning for Long-Horizon World Models

arXiv에 게시된 'WorldCompass: Reinforcement Learning for Long-Horizon World Models' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #World Models #Video Generation #Autoregressive Generation #Long-Horizon #Post-training #Diffusion Models #Reward Functions

2026년 2월 9일

[논문리뷰] Weak-Driven Learning: How Weak Agents make Strong Agents Stronger

arXiv에 게시된 'Weak-Driven Learning: How Weak Agents make Strong Agents Stronger' 논문에 대한 자세한 리뷰입니다.

#Review #Weak-Driven Learning #LLM Optimization #Post-training #Gradient Amplification #Curriculum Learning #Knowledge Distillation #Mathematical Reasoning #Code Generation

2026년 2월 9일

[논문리뷰] Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control

Yao Su이 arXiv에 게시한 'Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control' 논문에 대한 자세한 리뷰입니다.

#Review #Humanoid Control #Reinforcement Learning #SAC #Model-Based RL #Pretraining #Finetuning #Physics-Informed World Model #Sim-to-Real Transfer

2026년 2월 9일

[논문리뷰] RelayGen: Intra-Generation Model Switching for Efficient Reasoning

arXiv에 게시된 'RelayGen: Intra-Generation Model Switching for Efficient Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Inference Optimization #Model Switching #Efficient Reasoning #Speculative Decoding #Runtime Adaptation #Discourse-Level Cues #Latency Reduction

2026년 2월 9일

[논문리뷰] Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning

arXiv에 게시된 'Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #Latent Iterative Reasoning #Adaptive Compute #Recurrent Neural Networks #Robotics #Transformer #Test-Time Scaling #Continuous Action Space

2026년 2월 9일

[논문리뷰] QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining

arXiv에 게시된 'QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining' 논문에 대한 자세한 리뷰입니다.

#Review #Alpha Mining #LLM-Driven Agents #Evolutionary Algorithms #Financial Markets #Factor Generation #Trajectory Optimization #Quantitative Investment

2026년 2월 9일

[논문리뷰] Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

Hanzhen Zhao이 arXiv에 게시한 'Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Large Language Models (MLLMs)#Modality Gap #Subspace Alignment #Unpaired Data #Representation Learning #Pretraining #Geometric Alignment

2026년 2월 9일

[논문리뷰] MOVA: Towards Scalable and Synchronized Video-Audio Generation

arXiv에 게시된 'MOVA: Towards Scalable and Synchronized Video-Audio Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video-Audio Generation #Diffusion Transformer #Multimodal AI #Lip Synchronization #Open Source #Data Curation #Dual-Tower Architecture #Cross-Attention

2026년 2월 9일

[논문리뷰] Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory

arXiv에 게시된 'Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Runtime Memory #Budget-Tier Routing #Reinforcement Learning #Performance-Cost Trade-off #Modular Memory Pipeline #Query-Aware Memory #Resource Management

2026년 2월 9일

[논문리뷰] LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning

Jia Zhang이 arXiv에 게시한 'LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Chemical Reasoning #Large Language Models (LLMs)#Chain-of-Thought (CoT)#Latent Space #Molecular Optimization #Inference Efficiency #Reinforcement Learning #Chemical AI

2026년 2월 9일

[논문리뷰] LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth

arXiv에 게시된 'LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Language Agents #Long Context #Context Rot #Benchmarking #Context Management #Tool Use #Agent Evaluation #Dynamic Environments

2026년 2월 9일

[논문리뷰] LLaDA2.1: Speeding Up Text Diffusion via Token Editing

arXiv에 게시된 'LLaDA2.1: Speeding Up Text Diffusion via Token Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Text Diffusion #Token Editing #Inference Acceleration #Mask-to-Token #Token-to-Token #Reinforcement Learning #Speedy Mode #Quality Mode

2026년 2월 9일

[논문리뷰] InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

Xiangchao Yan이 arXiv에 게시한 'InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic AI #Scientific Discovery #Long-Horizon Reasoning #Structured Memory #Knowledge Graph #Experimental Optimization #Multi-disciplinary

2026년 2월 9일

[논문리뷰] GISA: A Benchmark for General Information-Seeking Assistant

arXiv에 게시된 'GISA: A Benchmark for General Information-Seeking Assistant' 논문에 대한 자세한 리뷰입니다.

#Review #Search Agents #Information Seeking #Benchmark #LLM-driven Agents #Human Trajectories #Deep and Wide Search #Deterministic Evaluation #Dynamic Evaluation

2026년 2월 9일

[논문리뷰] GEBench: Benchmarking Image Generation Models as GUI Environments

arXiv에 게시된 'GEBench: Benchmarking Image Generation Models as GUI Environments' 논문에 대한 자세한 리뷰입니다.

#Review #GUI Generation #Image Generation Models #Benchmark #Temporal Coherence #Spatial Grounding #Evaluation Metric #Vision Language Models

2026년 2월 9일