Abstract is missing.
- AVATAR-AGENT: A Multi-Agent System for Expressive 3D Avatar GenerationJason Ding, Rohan Gangaraju, Krishna C. Garikipati, Foad Dabiri, Chang Xu. 1-8 [doi]
- Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI SystemsSreemaee Akshathala, Bassam Adnan, Mahisha Ramesh, Karthik Vaidhyanathan, Basil Muhammed, Kannan Parthasarathy. 9-17 [doi]
- An Agentic System for LLM-Driven Public Transportation Analytics: A Practical Application and Case Study in Salvador-BrazilLucas T. Borges, Fei Tony Liu, Tatiane N. Rios, Marcos Vinicius Ferreira, Clovis Carmo, Danilo Barbosa Coimbra, Jorge Nery, Matheus Souza, Noe O. Garcia, Albert Bifet, Ricardo Araújo Rios. 18-25 [doi]
- CPEMH: An Agentic Framework for Prompt-Driven Behavior Evaluation and Assurance in Foundation-Model Systems for Mental Health ScreeningGiuliano Lorenzoni, Ivens Da Silva Portugal, Paulo S. C. Alencar, Donald D. Cowan. 26-30 [doi]
- Progressive Gated Co-Teaching for Weakly Supervised Deepfake DetectionRui Lang, Guangsheng Yu, Qin Wang 0008, Xu Wang 0004. 31-39 [doi]
- AI in Insurance: Adaptive Questionnaires for Improved Risk ProfilingDiogo Silva, João Teixeira, Bruno Lima. 40-47 [doi]
- Context Matters: Evaluating MCP-Based Context-Aware AI - A Case Study of Email Communications in Nonprofit OrganizationsNitin Gupta, Jayani Samaraweera, Raaj Chatterjee, Riya Shrestha, Trinity West, Daniela Damian. 48-55 [doi]
- ContReAct: A Feedback-Based Architecture for Continuous Agentic OperationStefan Szeider. 56-62 [doi]
- Decoding the Configuration of AI Coding Agents: Insights from Claude Code ProjectsHélio Victor Flexa dos Santos, Vitor Costa, João Eduardo Montandon, Marco Túlio Valente. 63-67 [doi]
- GeoAIAgent-Agentic workflow for automated geospatial data managementLeonardo Pondian Tizzei, Gabrielle Nyirjesy, Levente J. Klein, Ildar Khabibrakhmanov, Maciel Zortea, Hiyam Debary, Mustansar Fiaz, James Barry, João Lucas de Sousa Almeida, Theodore van Kessel, Segev Shlomov, Juan Bernabé-Moreno. 68-72 [doi]
- Agents - The Missing Piece in the Cognitive Cloud ContinuumSergio Moreschini, Diyaz Yakubov, Antti Kolehmainen, David Hästbacka. 78-82 [doi]
- Toward Author-Guided Review: An Agentic Architecture for Reflective Code ReviewNicole Davila, Igor Wiese. 83-87 [doi]
- LLM-X: A Scalable Negotiation-Oriented Exchange for Communication Among Personal LLM AgentsGiuliano Lorenzoni, Paulo S. C. Alencar, Donald D. Cowan. 88-95 [doi]
- AgentFixer: From Failure Detection to Fix Recommendations in Agentic SystemsHadar Mulian, Sergey Zeltyn, Ido Levy, Liane Galanti, Avi Yaeli, Segev Shlomov. 96-103 [doi]
- SWEnergy: An Empirical Study on Energy Efficiency in Agentic Issue Resolution Frameworks with SLMsArihant Tripathy, Ch Pavan Harshit, Karthik Vaidhyanathan. 104-111 [doi]
- Not All Problems Are Nails, Not All Tools Should Be Hammers: A Position Paper on Agent Usage in Software Engineering TasksJuuso Rytilahti, Panu Puhtila, Oshani Weerakoon, Erkki Kaila, Tuomas Mäkilä. 112-119 [doi]
- A Catalogue of Evaluation Metrics for LLM-Based Multi-Agent Frameworks in Software EngineeringIngrid Lima, Vitor Linhares, Anderson Martins Gomes, Paulo Henrique Maia. 120-124 [doi]
- From Stateless Code Generation to Living Ontologies: Business Autonomous Entities in ActionAnderson Martins Gomes, Paulo Henrique M. Maia, Vitor Fontenele de Oliveira Linhares, Ingrid Lima Vieira. 125-134 [doi]
- Using Copilot Agent Mode to Automate Library Migration: A Quantitative AssessmentAylton Almeida, Marco Túlio Valente, Laerte Xavier. 135-139 [doi]
- TALM: Dynamic Tree-Structured Multi-Agent Framework with Long-Term Memory for Scalable Code GenerationMing-Tung Shen, Yuh-Jzer Joung. 144-151 [doi]
- From Business Meetings to Requirement Artifacts: An Agentic AI Approach with MARAREMalik Abdul Sami, Gessé Evangelista, Kai-Kristian Kemell, Luciana Zaina, Muhammad Waseem, Zheying Zhang, Pekka Abrahamsson. 152-156 [doi]
- Toward Agentic Software Project Management: A Vision and RoadmapLakshana Iruni Assalaarachchi, Zainab Masood, Rashina Hoda, John Grundy 0001. 157-164 [doi]
- PerfBench: Can Agents Resolve Real-World Performance Bugs?Spandan Garg, Roshanak Zilouchian Moghaddam, Neel Sundaresan. 165-172 [doi]
- Building LLM-Based Voice Agents for Requirements Elicitation: An Experience Report on Early PrototypesOshani Weerakoon, Tuomas Mäkilä, Erkki Kaila, Shola Oyedeji. 173-180 [doi]
- Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and VocabularyRashina Hoda. 181-185 [doi]