[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…
[AI Paper] The Orchestration of Multi-Agent Systems: Architectures, Protocols, and Enterprise Adoption
The Orchestration of Multi-Agent Systems: Architectures, Protocols, and Enterprise Adoption Meta Information 항목 내용 저자 Apoorva Adimulam, Rajesh Gupta, Sumit Kumar arXiv ID 2601.13671v1 링크 arXiv Abstract | PDF 분야 Multi-Agent Systems, AI Orchestration,…
[AI Paper] 📄 Self-RAG: Learning to Retrieve, Generate, and Critique
📄 Self-RAG: Learning to Retrieve, Generate, and Critique 📋 메타 정보 항목 내용 논문 제목 Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection 저자 Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, Hannaneh Hajishirzi 소속 University of…
[AI Paper] 📄 Reflexion: Language Agents with Verbal Reinforcement Learning
📄 Reflexion: Language Agents with Verbal Reinforcement Learning 📋 메타 정보 항목 내용 저자 Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao 소속 Northeastern University (Khoury College), MIT, Princeton University 발표처…
[AI Paper] 📄 ReAct: Synergizing Reasoning and Acting in Language Models
📄 ReAct: Synergizing Reasoning and Acting in Language Models 📋 메타 정보 항목 내용 저자 Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao 소속 Princeton University (Department of Computer Science), Google Research (Brain Team)…