Review

[논문리뷰] The Responsibility Vacuum: Organizational Failure in Scaled Agent Systems

Roman Bondar이 arXiv에 게시한 'The Responsibility Vacuum: Organizational Failure in Scaled Agent Systems' 논문에 대한 자세한 리뷰입니다.

#Review #Responsibility Vacuum #Scaled Agent Systems #Organizational Failure #CI/CD Pipelines #Human Verification Capacity #Authority-Capacity Mismatch #AI Governance #Ritualized Approval

2026년 1월 21일

[논문리뷰] RoboBrain 2.5: Depth in Sight, Time in Mind

Yuheng Ji이 arXiv에 게시한 'RoboBrain 2.5: Depth in Sight, Time in Mind' 논문에 대한 자세한 리뷰입니다.

#Review #Embodied AI #Foundation Model #3D Spatial Reasoning #Temporal Value Estimation #Robotics #Manipulation #Multimodal Learning

2026년 1월 21일

[논문리뷰] Rethinking Video Generation Model for the Embodied World

arXiv에 게시된 'Rethinking Video Generation Model for the Embodied World' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Embodied AI #Robotics Benchmark #RBench #Robotics Dataset #RoVid-X #Physical Plausibility #Task Completion

2026년 1월 21일

[논문리뷰] Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning

arXiv에 게시된 'Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Chain-of-Thought (CoT)#Large Language Models (LLMs)#Vision Language Models (VLMs)#Latent Reasoning #Visual Modality #Image Rendering #Computational Efficiency #Knowledge Distillation

2026년 1월 21일

[논문리뷰] Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis

Jihwan Lee이 arXiv에 게시한 'Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Speech #Accent Control #Phonological Rules #Speaker Embeddings #Speech Synthesis #Disentanglement #Accent Classification

2026년 1월 21일

[논문리뷰] Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance

arXiv에 게시된 'Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Agent Framework #LLM Agents #Peer Review #Rebuttal Generation #Evidence-centric Planning #Transparency #Human-in-the-loop

2026년 1월 21일

[논문리뷰] Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics

arXiv에 게시된 'Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Systems #Formal Theorem Proving #Large Language Models (LLMs)#Lean Theorem Prover #Multi-Agent Systems #Code Generation #Automated Reasoning #Human-AI Collaboration

2026년 1월 21일

[논문리뷰] MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents

Samiul Alam이 arXiv에 게시한 'MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Deep Research #Research Agents #Benchmark #Evaluation Framework #Retrieval-Augmented Generation #Large Multimodal Models #Visual Grounding #Citation Analysis

2026년 1월 21일

[논문리뷰] Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models

arXiv에 게시된 'Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Prompt Engineering #Large Language Models #Causal Attention #Multiple-Choice QA #Prompt Order Sensitivity #Information Bottleneck #Decoder-only Transformers

2026년 1월 21일

[논문리뷰] FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments

arXiv에 게시된 'FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments' 논문에 대한 자세한 리뷰입니다.

#Review #Financial AI Agents #Security Benchmark #Execution-Grounded #LLM Safety #Prompt Injection #Jailbreaking #Compliance #Vulnerability Assessment

2026년 1월 21일

[논문리뷰] Facilitating Proactive and Reactive Guidance for Decision Making on the Web: A Design Probe with WebSeek

Arpit Narechania이 arXiv에 게시한 'Facilitating Proactive and Reactive Guidance for Decision Making on the Web: A Design Probe with WebSeek' 논문에 대한 자세한 리뷰입니다.

#Review #Mixed-Initiative AI #Human-AI Collaboration #Web Data Analysis #Proactive Guidance #Large Language Models (LLMs)#Browser Extension #Data-Centric Design

2026년 1월 21일

[논문리뷰] FARE: Fast-Slow Agentic Robotic Exploration

Jingsong Liang이 arXiv에 게시한 'FARE: Fast-Slow Agentic Robotic Exploration' 논문에 대한 자세한 리뷰입니다.

#Review #Robotic Exploration #LLM #Reinforcement Learning #Fast-Slow Thinking #Hierarchical Planning #Agentic AI #Graph Reasoning

2026년 1월 21일

[논문리뷰] Agentic Reasoning for Large Language Models

arXiv에 게시된 'Agentic Reasoning for Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Reasoning #LLM Agents #Self-Evolving AI #Multi-Agent Systems #Planning #Tool Use #Retrieval-Augmented Generation #Reinforcement Learning

2026년 1월 21일

[논문리뷰] AgentEHR: Advancing Autonomous Clinical Decision-Making via Retrospective Summarization

arXiv에 게시된 'AgentEHR: Advancing Autonomous Clinical Decision-Making via Retrospective Summarization' 논문에 대한 자세한 리뷰입니다.

#Review #Clinical Decision-Making #LLM Agents #EHR #Retrospective Summarization #Long-Context Reasoning #Experience Replay #Healthcare AI

2026년 1월 21일

[논문리뷰] UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation

arXiv에 게시된 'UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Chest X-Ray #Medical Foundation Model #Autoregressive Model #Diffusion Model #Multimodal Learning #Image Understanding #Image Generation #Cross-Modal Attention

2026년 1월 20일

[논문리뷰] Toward Efficient Agents: Memory, Tool learning, and Planning

arXiv에 게시된 'Toward Efficient Agents: Memory, Tool learning, and Planning' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Agent Efficiency #Memory Management #Tool Learning #AI Planning #Resource Optimization #Cost-Performance Trade-off

2026년 1월 20일

[논문리뷰] ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents

arXiv에 게시된 'ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Process Reward Models #Tool-using Agents #Benchmark #Reinforcement Learning #Large Language Models #Reward-guided Search #Agent Evaluation #Step-level Rewards

2026년 1월 20일

[논문리뷰] Think3D: Thinking with Space for Spatial Reasoning

Yuhan Wu이 arXiv에 게시한 'Think3D: Thinking with Space for Spatial Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Spatial Reasoning #3D Reconstruction #VLM Agents #Tool Calling #Reinforcement Learning #Novel View Synthesis #Iterative Exploration

2026년 1월 20일

[논문리뷰] SciCoQA: Quality Assurance for Scientific Paper--Code Alignment

arXiv에 게시된 'SciCoQA: Quality Assurance for Scientific Paper--Code Alignment' 논문에 대한 자세한 리뷰입니다.

#Review #Reproducibility #Paper-Code Discrepancy #Code Alignment #LLM Evaluation #Synthetic Data Generation #Quality Assurance #Scientific Automation

2026년 1월 20일

[논문리뷰] PRiSM: Benchmarking Phone Realization in Speech Models

arXiv에 게시된 'PRiSM: Benchmarking Phone Realization in Speech Models' 논문에 대한 자세한 리뷰입니다.

#Review #Phone Recognition #Speech Models #Benchmarking #Phonetic Analysis #Cross-lingual Speech #LALMs #Intrinsic Evaluation #Extrinsic Evaluation

2026년 1월 20일