[AI Paper] Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub
Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub 📌 1단계: 기본 정보 항목 내용 제목 Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub 저자 Ramtin Ehsani, Sakshi Pathak, Shriya Rawal,…
[AI Paper] VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning
VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning 📌 1단계: 기본 정보 제목: VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning 저자: Chenglin Li (Zhejiang University, Shanghai Innovation Institute) Qianglong Chen (Zhejiang…
[AI Paper] TransportAgents: a multi-agents LLM framework for traffic accident severity prediction
TransportAgents: a multi-agents LLM framework for traffic accident severity prediction 📌 1단계: 기본 정보 항목 내용 제목 TransportAgents: a multi-agents LLM framework for traffic accident severity prediction 저자 Zhichao Yang¹, Jiashu He², Jinxuan Fan³, Cirillo…
[AI Paper] 📄 Towards Reliable ML Feature Engineering via Planning in Constrained-Topology of LLM Agents
📄 Towards Reliable ML Feature Engineering via Planning in Constrained-Topology of LLM Agents 메타 정보 저자: Himanshu Thakur, Anusha Kamath, Anurag Muthyala, Dhwani Sanmukhani, Smruthi Mukund, Jay Katukuri 출처: arXiv:2601.10820v1 발표일: 2026년 1월 라이선스: CC BY 4.0…
[AI Paper] Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement
Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement 메타 정보 항목 내용 저자 Jian Zhang, Zhangqi Wang, Zhiyuan Wang, Weiping Fu, Yu He arXiv ID 2601.13481v1 링크 arXiv Abstract | PDF 주제 Multi-Agent…
[AI Paper] 📄 Toolformer: Language Models Can Teach Themselves to Use Tools
📄 Toolformer: Language Models Can Teach Themselves to Use Tools 📋 메타 정보 저자: Timo Schick, Jane Dwivedi-Yu, Roberto Dessi, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, Thomas Scialom 기관: Meta AI Research, Universitat Pompeu Fabra…
[AI Paper] 📄 ToolLLM: Facilitating LLMs to Master 16000+ APIs
📄 ToolLLM: Facilitating LLMs to Master 16000+ APIs 📋 메타 정보 항목 내용 논문 제목 ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs 발표 ICLR 2024 (Spotlight) 저자 Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu 외 다수 소속 Tsinghua University,…
[AI Paper] 📄 Tool Learning with Foundation Models
📄 Tool Learning with Foundation Models 📋 메타 정보 항목 내용 제목 Tool Learning with Foundation Models 저자 Yujia Qin, Shengding Hu, Yankai Lin, Weize Chen, Ning Ding 외 40+ 연구자 소속 Tsinghua University, Renmin University, UIUC, NYU, CMU, Beijing University of Posts…
[AI Paper] The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [!summary] 논문 개요 이 논문은 LLM 기반 AI 에이전트의 행동 이면에 있는 내부 동인을 파악하는 새로운 프레임워크인 Agentic Attribution을 제안합니다. 기존의 실패 원인 규명(Failure Attribution) 접근법에서 한 걸음 더 나아가, 성공하더라도 부적절한 의사결정 프로세스를…
[AI Paper] 📄 The Responsibility Vacuum: Organizational Failure in Scaled Agent Systems
📄 The Responsibility Vacuum: Organizational Failure in Scaled Agent Systems 📌 1단계: 기본 정보 항목 내용 제목 The Responsibility Vacuum: Organizational Failure in Scaled Agent Systems 저자 Oleg Romanchuk, Roman Bondar arXiv ID 2601.15059v1 발행일 2026년 1월 21일 분야 Computer…