Table of Contents

• optimize_anything: Unified Text Optimization can Outperform Specialized SystemsLakshya A. Agrawal, Donghyun Lee, Shangyin Tan, Wenjie Ma, Karim Elmaaroufi, Rohit Sandadi, Sanjit A. Seshia, Koushik Sen, Dan Klein 0001, Ion Stoica, Joseph E. Gonzalez, Omar Khattab, Alexandros G. Dimakis, Matei Zaharia. 1-16 [doi]
• Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDPIgor Bogdanov, Chung-Horng Lung, Thomas Kunz, Jie Gao, Adrian Taylor, Marzia Zaman. 17-45 [doi]
• Tressoir: Unifying Online, Offline, and HIL Design and Evolution of Multi-Agent Systems via Interpretable BlueprintsAmadou Latyr Ngom, Ziniu Wu, Jason Mohoney, James Moore, Alex L. Zhang, Samuel Madden 0001, Tim Kraska. 46-60 [doi]
• Glia: A Human-Inspired AI for Automated Systems Design and OptimizationPouya Hamadanian, Pantea Karimi, Arash Nasr-Esfahany, Kimia Noorbakhsh, Joseph Chandler, Ali ParandehGheibi, Mohammad Alizadeh, Hari Balakrishnan. 61-84 [doi]
• A Language for Describing Agentic LLM ContextsNoga Peleg Pelc, Gal A. Kaminka, Yoav Goldberg. 85-102 [doi]
• Retrieval-Augmented LLMs for Security Incident AnalysisXavier Cadet, Aditya Vikram Singh 0002, Harsh Mamania, Edward Koh, Alex Fitts, Dirk Van Bruggen, Simona Boboila, Peter Chin 0001, Alina Oprea. 103-123 [doi]
• Improving Coherence and Persistence in Agentic AI for System OptimizationPantea Karimi, Kimia Noorbakhsh, Mohammad Alizadeh, Hari Balakrishnan. 124-160 [doi]
• fastWorkflow: Closing the Performance Gap Between Small and Frontier Language Models for Conversational AgentsSanchit Satija, Aditya Bhatt 0005, Priyanshu Jani, Dhar Rawal. 161-180 [doi]
• TraceFix: Repairing Agent Coordination Protocols with TLA+ CounterexamplesShuren Xia, Qiwei Li 0006, Taqiya Ehsan, Jorge Ortiz 0001. 181-196 [doi]
• Composing Policy Gradients and Prompt Optimization for Language Model ProgramsNoah Ziems, Dilara Soylu, Lakshya A. Agrawal, Isaac Miller, Liheng Lai, Chen Qian, Kaiqiang Song, Meng Jiang, Dan Klein 0001, Matei Zaharia, Karel D'Oosterlinck, Christopher Potts, Omar Khattab. 197-213 [doi]
• LiveGraph: A Compound AI System for Evolving Knowledge Graph Construction from Streaming DataRakshit Agrawal, Pritesh Kanani, Madhu Sudan, Ashish Gujarathi, Dhruv Srivastava, Mikita Reut, Naveen Shrivastava. 214-223 [doi]
• Expansion-Contraction: A Multi-Agent Graph Traversal Pattern for Compound AI SystemsAiham Taleb, Zainab Afolabi, Joao Sousa, Mathias Seidel. 224-238 [doi]
• Vista: Verifier-in-the-Loop Agentic Reinforcement Learning for Quantum Program SynthesisCong Yu, Tuo Shi, Valter Uotila, Shilong Deng, Lei You 0002, Bo Zhao 0019. 239-252 [doi]
• Robust Agent Compensation (RAC): Teaching AI Agents to CompensateSrinath Perera, Kaviru Hapuarachchi, Frank Leymann, Rania Khalaf. 253-262 [doi]
• Dossier: Deep Research via Ledger-Driven Branching Search and Query Encoding LearningOm Chabra, Noah Ziems, Meng Jiang, Omar Khattab, Hari Balakrishnan. 263-275 [doi]
• Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent AdaptationJackson Hassell, Dan Zhang 0025, Hannah Kim 0001, Tom M. Mitchell, Estevam Hruschka. 276-291 [doi]
• FORGE: Self-Evolving Agent Memory With No Weight Updates via Population BroadcastIgor Bogdanov, Chung-Horng Lung, Thomas Kunz, Jie Gao, Adrian Taylor, Marzia Zaman. 292-310 [doi]
• The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent DebateBlaz Bertalanic, Carolina Fortuna. 311-329 [doi]
• How to Steer Your Multi-Agent System: Human-LLM Collaborative PlanningZeyu He, Hannah Kim 0001, Dan Zhang 0025, Estevam Hruschka. 330-347 [doi]
• Scideator: Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty EvaluationMarissa Radensky, Simra Shahid, Raymond Fok, Pao Siangliulue, Tom Hope, Daniel S. Weld. 348-374 [doi]
• Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool CallingNaoki Otani, Nikita Bhutani, Hannah Kim 0001, Dan Zhang 0025, Estevam Hruschka. 375-403 [doi]
• Open Agent Specification: Enabling Cross-Framework Comparison of AI AgentsSoufiane Amini, Yassine Benajiba, Cesare Bernardis, Paul Cayet, Hassan Chafi, Abderrahim Fathan, Louis Faucon, Damien Hilloulin, Sungpack Hong, Ingo Kossyk, Tirthankar Lahiri, Tran Minh Son Le, Rhicheek Patra, Sujith Ravi, Jonas Schweizer, Jyotika Singh, Shailender Singh, Weiyi Sun, Kartik Talamadupula, Jerry Xu. 404-418 [doi]
• AI Realtor: Towards Grounded Persuasive Language Generation for Automated CopywritingJibang Wu, Chenghao Yang 0001, Yi Wu 0013, Simon Mahns, Chaoqi Wang, Hao Zhu, Fei Fang 0001, Haifeng Xu. 419-444 [doi]
• MARVIS: Modality Adaptive Reasoning over VISualizationsBenjamin Feuer, Lennart Purucker, Oussama Elachqar, Chinmay Hegde. 445-472 [doi]
• Equitable Ranking in Heterogeneous Marketplace Ecosystems: A Foundation Model Framework for Quality-Aware FairnessSaurabh Krishna Kansara. 473-482 [doi]
• Trace-Level Analysis of Information Contamination in Multi-Agent SystemsAnna Mazhar, Huzaifa Suri, Sainyam Galhotra. 483-496 [doi]
• ViBench: A Benchmark on Vibe CodingPeter Zhong, Pashootan Vaezipoor, Fuyang Cui, Vaibhav Kumar, James Austin, Azin Asgarian, Toby Ho, Paul Inder, Imen Kedir, Zhen Li, Nicholas Ondo, Asna Shafiq, Ibrahim Sheikh, Edouard Sioufi, Setareh Soltanieh, Ben Wilde, Jacky Zhao, Ryan Carelli, Heather Miller, Michele Catasta. 497-513 [doi]
• Vibe Code Bench: Evaluating AI Models on End-to-End Web Application DevelopmentHung Tran, Langston Nashold, Rayan Krishnan, Antoine Bigeard, Alex Gu. 514-536 [doi]
• Does Socialization Emerge in AI Agent Society? A Case Study of MoltbookMing Li 0010, Xirui Li, Tianyi Zhou 0001. 537-550 [doi]
• Reasoning-Intensive RegressionDiane Tchuindjo, Omar Khattab. 551-583 [doi]
• Willful Disobedience: Automatically Detecting Failures in Agentic TracesReshabh K. Sharma, Shraddha Barke, Benjamin Zorn 0001. 584-596 [doi]
• Why Johnny Can't Use Agents: Industry Aspirations vs. User Realities with AI AgentsPradyumna Shome, Sashreek Krishnan, Sauvik Das. 597-619 [doi]
• OpaqueToolsBench: Learning Nuances of Tool Behavior Through InteractionSkyler Hallinan, Thejas Venkatesh, Xiang Ren 0001, Sai Praneeth Karimireddy, Ashwin Paranjape, Yuhao Zhang 0004, Jack Hessel. 620-638 [doi]
• Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuelAadyaa Maddi, Prakhar Naval, Deepti Mande, Muckai Girish, Shane Duan, Vyas Sekar. 639-673 [doi]
• DraftNEPABench: A Benchmark for Drafting NEPA Document Sections with Coding AgentsAnurag Acharya 0002, Bishal Lakha, Rounak Meyur, Rohan Nuttall, Sarthak Chaturvedi, Anika Halappanavar, Leah Hare, Lin Zeng, Mike Parker, Sai Munikoti, Sameera Horawalavithana. 674-688 [doi]
• Benchmarking Agents in Insurance Underwriting EnvironmentsAmanda Dsouza, Ramya Ramakrishnan, Charles Dickens, Bhavishya Pohani, Christopher M. Glaze. 689-701 [doi]
• Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language ModelsNimet Beyza Bozdag, Shuhaib Mehri, Gokhan Tur, Dilek Hakkani-Tur. 702-726 [doi]
• Does Safety Molt? Evaluating LLM Safety in Multi-Agent Social EnvironmentsAman Priyanshu, Supriti Vijay, Esha Pahwa. 727-737 [doi]
• A HIPAA-Compliant Architecture for Agentic Clinical AI SystemsHimanshu Tripathi, Subash Neupane, Sudip Mittal, Shahram Rahimi 0001, Vibhuti Gupta. 738-754 [doi]
• Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply ChainLéo Boisvert, Abhay Puri, Chandra Kiran Reddy Evuru, Nazanin Mohammadi Sepahvand, Nicolas Chapados, Quentin Cappart, Alexandre Lacoste, Krishnamurthy Dvijotham, Alexandre Drouin, Jason Stanley. 755-772 [doi]
• SAPO: Secure Automated Prompt Optimization via Multi-Agent CollaborationEmmanuel Aboah Boateng, Zachary Johnson, Tian Xia, Sarah Zhang, Aidan Jay, Junyao Feng, Aditya Mate, Ehi Nosakhare. 773-784 [doi]
• The Verifier Tax: Horizon Dependent Safety-Success Tradeoffs in Tool Using LLM AgentsTanmay Sah, Vishal Srivastava, Dolly Sah, Kayden Jordan. 785-799 [doi]
• MoltGraph: A Longitudinal Temporal Graph Dataset of Moltbook for Coordinated-Agent DetectionKunal Mukherjee, Cuneyt Gurcan Akcora, Murat Kantarcioglu. 800-811 [doi]
• Securing Agents With Tracked CapabilitiesMartin Odersky, Yaoyu Zhao, Yichen Xu 0008, Oliver Bracevac, Cao Nguyen Pham. 812-838 [doi]
• Exploring and Developing a Pre-Model Safeguard with Draft ModelsHongyu Cai, Arjun Arunasalam, Yiming Liang, Antonio Bianchi, Z. Berkay Celik. 839-854 [doi]
• Who Decides the Trade-off? Resolution Policy as Delegation Governance in Autonomous AgentsKoji Yamazaki. 855-861 [doi]
• Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool UseFrancisco Javier Arceo, Varsha Prasad Narsing. 862-872 [doi]
• When Harmful Intent Dissolves into Technical Detail: How Safe Are Coding Agents Against Cyber Misuse?Xiangzhe Xu, Shiwei Feng 0002, Guangyu Shen, Xiangyu Zhang 0001. 873-889 [doi]
• Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity ConstraintsJelena Markovic-Voronov, Kayhan Behdin, Yuanda Xu, Zhengze Zhou, Zhipeng Wang, Rahul Mazumder. 890-916 [doi]
• Scaling Textual Gradients via Sampling-Based MomentumZixin Ding, Junyuan Hong, Zhan Shi, Tianhao Wang 0001, Zinan Lin 0001, Li Yin, Meng Liu, Zhangyang Wang, Yuxin Chen. 917-952 [doi]
• FedMECA: Scalable Federated Learning via Memory-Efficient and Concurrent AggregationZhonghao Chen, Duo Zhang, Xiaoyi Lu 0001. 953-963 [doi]
• Echo: KV-Cache-Free Associative Recall with Spectral Koopman OperatorsAnupama Sridhar, Alexander Johansen. 964-989 [doi]
• FLASC: Federated LoRA with Sparse CommunicationKevin Kuo, Arian Raje, Kousik Rajesh, Virginia Smith. 990-1008 [doi]
• XGrammar-2: Dynamic and Efficient Structured Generation Engine for Agentic LLMsLinzhang Li, Yixin Dong, Guanjie Wang, Ziyi Xu, Alexander Jiang, Tianqi Chen 0001. 1009-1022 [doi]
• CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic RetrievalAdnan Qidwai, Anand Eswaran, Sonam Mishra, Jaydeep Sen, Sachindra Joshi. 1023-1036 [doi]
• SwiftFusion: Scalable Sequence Parallelism for Distributed Inference of Diffusion Transformers on GPUsJiacheng Yang, Jun Wu, Yaoyao Ding, Zhiying Xu, Yida Wang 0003, Gennady Pekhimenko. 1037-1050 [doi]
• AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer DevicesDzung Pham, Kleomenis Katevas, Ali Shahin Shamsabadi, Hamed Haddadi 0001. 1051-1069 [doi]
• Understanding and Improving Communication Performance in Multi-node LLM InferencePrajwal Singhania, Siddharth Singh, Lannie Dalton Hough, Akarsh Srivastava, Harshitha Menon, Charles Fredrick Jekel, Abhinav Bhatele. 1070-1083 [doi]
• SEAR: Schema-Based Evaluation and Routing for LLM GatewaysZecheng Zhang, Han Zheng, Yue Xu. 1084-1099 [doi]
• Supervisory Control Theory for LLM RevisionWangfan Li, Carlos Toxtli. 1100-1108 [doi]
• Nexa: Automatically Surfacing Business Impacting Insights in E-commerce ApplicationsSmart Sun, Sayan Sinha, Haijie Wu, Joel Goldfoot, Aditya Ganjam, Jibin Jhan, Evan Chan, Qichu Gong, Vipul Harsh, Bo Lin, Pawas Ranjan, Wei Wang 0010, Zhan Yang, Ningning Hu, B. Aditya Prakash, Vyas Sekar, Hui Zhang 0001. 1109-1113 [doi]
• EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning ToolsBoer Zhang, Mingyan Wu, Dongzhuoran Zhou, Yuqicheng Zhu, Wendong Fan, Puzhen Zhang, Zifeng Ding, Guohao Li 0001, Yuan He 0008. 1114-1118 [doi]
• From Bug Report to Pull Request: An Autonomous Agent Pipeline for Production Issue ResolutionRoberto Milev, Uday Kanagala, Chris Cholette. 1119-1122 [doi]
• HearthNet: Edge Multi-Agent Orchestration for Smart HomesZhonghao Zhan, Krinos Li, Yefan Zhang, Hamed Haddadi 0001. 1123-1127 [doi]
• Parallel Environments for AgentsShangyin Tan, Jialin Zhang, Matei Zaharia. 1128-1134 [doi]
• TRACE: A Multi-Agent System for Natural Language-Driven Social Graph InvestigationArunachaleshwar Ravichandran, Nicole Chen, Ankitesh Gupta, Antonios Broumas, Ioannis C. Konstantakopoulos, Seyoung Park. 1135-1141 [doi]
• Agent-Aided Design for Dynamic CAD ModelsMitch Adler, Matthew Russo, Michael J. Cafarella. 1142-1146 [doi]
• Steering Agent Behavior via a Domain Expert-Driven Alignment-to-Optimization BridgeWesley Pasfield. 1147-1155 [doi]
• Scaling Expert Feedback with Reflective Edit Propagation in Compositional Knowledge BasesJiajing Guo, Xueming Li, Jorge Henrique Piazentin Ono, Wenbin He, Liu Ren. 1156-1164 [doi]
• L.A.K.E.: Logic Agent for Knowledge Extraction in Data PlanningJean-Flavien Bussotti, Naoki Otani, Eser Kandogan. 1165-1171 [doi]
• cotomi Act: Learning to Automate Work by Watching YouMasafumi Oyamada, Kunihiro Takeoka, Kosuke Akimoto, Ryoma Obara, Masafumi Enomoto, Haochen Zhang, Daichi Haraguchi, Takuya Tamura. 1172-1178 [doi]
• Multi-Agent Position Classification with Tool Orchestration: Use Case System for Occupational Taxonomy MappingVahid Farajijobehdar, Ilknur Köseoglu Sari, Nazim Kemal Üre, Engin Zeydan. 1179-1186 [doi]
• Agent 4: Teamwork and Collaboration for Vibe-CodingPeter Yong Zhong, Jacky Zhao, Edouard Sioufi, James Austin, Brian Pool, Luis Héctor Chávez, Adi Dahiya, William Ernst, Dawei Feng, Daniel Ryan Furman, Devin Halladay, Toby Ho, Zade Kaylani, Imen Kedir, Vaibhav Kumar, Zhen Li, Haya Odeh, Nicholas Ondo, Darsh Patel, Alec Wang, Jordan Walke, Poorva Potnis, Ibrahim Sheikh, Michele Catasta. 1187-1192 [doi]
• Genflow Ad Studio: A Compound AI Architecture for Brand-Aligned, Self-Correcting Video GenerationDebanshu Das, Lavi Nigam, Sunil Kumar Jang Bahadur, Gopala Dhar. 1193-1198 [doi]
• Demonstration of Pneuma-Seeker: An Agentic System for Reifying and Fulfilling Information Needs on Tabular DataMuhammad Imam Luthfi Balaka, Raul Castro Fernandez. 1199-1203 [doi]
• GRAFT: gRPC-Routed Agent Framework for Tasking in Edge and Personal DevicesChinmay Shringi, Alon Hillel-Tuch, Sariya Rizwan. 1204-1212 [doi]
• SQLsaber: Agentic SQL Assistant for Efficient and High-Accuracy Natural Language Database ExplorationSarthak Jariwala. 1213-1217 [doi]
• DRCY: Agentic Hardware Design ReviewsKyle Dumont, Nick Herbert, Hayder Tirmazi, Shrikanth Upadhayaya. 1218-1222 [doi]
• SkyDiscover: A Flexible, Adaptive Framework for AI-Driven Scientific and Algorithmic DiscoveryShu Liu, Mert Cemri, Shubham Agarwal, Alexander Krentsel, Ashwin Naren, Qiuyang Mang, Zhifei Li, Akshat Gupta, Monishwaran Maheswaran, Audrey Cheng, Melissa Z. Pan, Ethan Boneh, Kannan Ramchandran, Koushik Sen, Matei Zaharia, Alexandros G. Dimakis, Ion Stoica. 1223-1227 [doi]
• ClinicBot: A Guideline-Grounded Clinical Chatbot with Prioritized Evidence RAG and Verifiable CitationsNavapat Nananukul, Mayank Kejriwal. 1228-1232 [doi]
• Complex Knowledge Curation using Agentic Ontological Notebook MemoryGully Burns, Paul Groth. 1233-1237 [doi]
• A Compound AI Agent for Conversational Grant DiscoveryZhisheng Tang, Mayank Kejriwal. 1238-1242 [doi]
• Peeking Under the Hood of Multi-Agent SystemsTie Ma, Yixi Chen 0001, Vaastav Anand, Alessandro Cornacchia, Amândio R. Faustino, Guanheng Liu, Shan Zhang 0001, Hongbin Luo, Suhaib A. Fahmy, Zafar Ayyub Qazi, Marco Canini. 1243-1247 [doi]
• Skilled AI Agents for Embedded and IoT Systems DevelopmentYiming Li, Yuhan Cheng, Mingchen Ma, Yihang Zou, Ningyuan Yang, Wei Cheng 0006, Hai Li 0001, Yiran Chen 0001, Tingjun Chen. 1248-1252 [doi]
• SREGym: A Live Training Ground for AI SRE Agents with High-Fidelity Failure DrillsJackson Clark, Yiming Su, Saad Mohammad Rafid Pial, Lily Gniedziejko, Tianyin Xu. 1253-1258 [doi]
• Introspectable, Updatable, and Uncertainty-aware Classification of Language Model Instruction-followingAllen Schmaltz. 1259-1269 [doi]
• Valkyrie: A Microservice-Based Framework for Scalable Evaluation of AI AgentsJarett Forzano, Omar Almatov, Langston Nashold, Nikil Ravi, Orestes Kassian. 1270-1274 [doi]
• Arena: Benchmarking AI Agent Frameworks Under Fixed-Model ConditionsRoberto Milev, Uday Kanagala. 1275-1279 [doi]
• Governance by Construction for Generalist AgentsSegev Shlomov, Iftach Shoham, Alon Oved, Ido Levy, Sami Marreed, Harold J. Ship, Offer Akrabi, Sergey Zeltyn, Avi Yaeli, Nir Mashkif. 1280-1287 [doi]
• Forge: Closing the Agentic Reliability Gap Between Self-Hosted and Frontier Language ModelsAntoine Emil Zambelli. 1288-1292 [doi]
• Hedwig: Dynamic Autonomy for Coding Agents Under Local OversightTanjal Shukla, Kevin Feng, Leijie Wang, Mohammad Rostami, Amy X. Zhang. 1293-1299 [doi]
• optimize_anything: A Universal API for Optimizing any Text ParameterLakshya A. Agrawal, Donghyun Lee, Shangyin Tan, Wenjie Ma, Karim Elmaaroufi, Sanjit A. Seshia, Koushik Sen, Dan Klein 0001, Ion Stoica, Joseph E. Gonzalez, Omar Khattab, Alexandros G. Dimakis, Matei Zaharia. 1300-1304 [doi]
• StigmergyRouter: A Fault-Aware Adaptive Routing Demo for Multi-Agent AI SystemsJing Du, Hang Zhao, Kenneth Huang. 1305-1309 [doi]
• Automatically Learning Skills for Coding AgentsShangyin Tan, Lakshya A. Agrawal, Rohit Sandadi, Dan Klein 0001, Koushik Sen, Alexandros G. Dimakis, Matei Zaharia. 1310-1315 [doi]
• Cornserve: A Distributed Serving System for Any-to-Any Multimodal ModelsJae-won Chung, Jeff J. Ma, Jisang Ahn, Yizhuo Liang 0001, Akshay Jajoo, Myungjin Lee, Mosharaf Chowdhury. 1316-1321 [doi]
• Orla: A Library for Serving LLM-Based Multi-Agent SystemsRana Shahout, Hayder Tirmazi, Minlan Yu, Michael Mitzenmacher. 1322-1326 [doi]
• Behavioral Fingerprints for LLM Endpoint Stability and IdentityJonah Leshin, Manish Shah, Ian Timmis, Daniel Kang. 1327-1331 [doi]
• Sentinel: Autonomous Architectural Governance Through Commit Intelligence Across Multi-Repository SystemsRoberto Milev, Uday Kanagala. 1332-1335 [doi]
• Pathfinder: Self-Improving Agent Trace Analysis via Adversarial Self-Play and Code ExecutionDhruv Atreja. 1336-1339 [doi]
• Agent Lifecycle Toolkit (ALTK): Reusable Middleware Components for Robust AI AgentsZidane Wright, Jason Tsay, Anupama Murthi, Osher Elhadad, Diego Del Rio, Saurabh Goyal, Kiran Kate, Jim Alain Laredo, Koren Lazar, Vinod Muthusamy, Yara Rizk. 1340-1344 [doi]
• Context Viewer: Turning LLM Contexts into Analyzable ArtifactsSrihari Sriraman, Michael Isaac, Atharva Raykar, Heather Miller. 1345-1352 [doi]
• PAGER: Proactive Monitoring Agent for Enterprise AI AssistantJunior Francisco Garcia Ayala, Sujan Dutta, Pranav Umakant Pujar, Sai Sree Harsha, Dan Luo, Nikhil Vasudeva, Bikas Saha, Pritom Baruah, Yunyao Li 0001. 1353-1361 [doi]
• Wily: High-Performance Complexity Gated-Feedback for AI Coding AgentsAnthony Shaw, Amin Beheshti. 1362-1366 [doi]
• Goal-Oriented Reliability and Self-Improvement for Multi-Agent SystemsVishwanath Katharki, Sainyam Galhotra. 1367-1371 [doi]
• AgentClick: A Skill-Based Human-in-the-Loop Review Layer for Terminal AI AgentsHaomin Zhuang, Hanwen Xing, Xiangliang Zhang 0001. 1372-1378 [doi]