Posters

Deadline: April 7, 2025

List of Accepted Papers

• 🥇 People’s Choice Best Paper (1st Place) An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science (opens in a new tab)
  Qiuhai Zeng*, Claire Jin*, Xinyue Wang, Yuhan Zheng, Qunhua Li

• 🥈 People’s Choice Best Paper (2nd Place) Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents (opens in a new tab)
  Yu Gu, Kai Zhang, Yuting Ning, Boyuan Zheng, Boyu Gou, Tianci Xue, Cheng Chang, Sanjari Srivastava, Yanan Xie, Peng Qi, Huan Sun, Yu Su

• Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Web Agents (opens in a new tab)
  Vardaan Pahuja, Yadong Lu, Corby Rosset, Boyu Gou, Arindam Mitra, Spencer Whitehead, Yu Su, Ahmed Awadallah

• CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation (opens in a new tab)
  Faria Huq, Zora Zhiruo Wang, Frank F. Xu, Tianyue Ou, Shuyan Zhou, Jeffrey P. Bigham*, Graham Neubig*

• From RAG to Memory: Non-Parametric Continual Learning for Large Language Models (opens in a new tab)
  Bernal Jimenez Gutierrez, Yiheng Shu, Weijian Qi, Sizhe Zhou, Yu Su

• Refusal-trained LLMs Are Easy Jailbroken as Browser Agents (opens in a new tab)
  Priyanshu Kumar, Elaine Lau, Saranya Vijayakumar, Tu (Alina) Trinh, Scale Red Team, Elaine Chang, Vaughn Robinson, Sean Hendryx, Shuyan Zhou, Matt Fredrikson, Summer Yue, Zifan (Sail) Wang

• AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents (opens in a new tab)
  Harsh Trivedi, Tushar Khot, Mareike Hartmann, Ruskin Manku, Vinty Dong, Edward Li, Shashank Gupta, Ashish Sabharwal, Niranjan Balasubramanian

• SimuRA: Towards General Goal-Oriented Agent via Simulative Reasoning Architecture with LLM-Based World Model (opens in a new tab)
  Mingkai Deng*, Jinyu Hou*, Zhiting Hu, Graham Neubig, Hongxia Jin, Yilin Shen, Eric P. Xing

• Should You Use Your Large Language Model to Explore or Exploit? (opens in a new tab)
  Keegan Harris, Alex Slivkins

• Direct Multi-Turn Preference Optimization for Language Agents (opens in a new tab)
  Wentao Shi, Mengqi Yuan, Junkang Wu, Qifan Wang, Fuli Feng

• An Illusion of Progress? Assessing the Current State of Web Agents (opens in a new tab)
  Tianci Xue, Weijian Qi, Tianneng Shi, Chan Hee Song, Boyu Gou, Dawn Song, Huan Sun, Yu Su

• Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks (opens in a new tab)
  Hanjiang Hu, Alexander Robey, Changliu Liu

• AI Agents for Personal Finance: Enhancing Credit Behavior, Budgeting Precision, and Spending Decisions (opens in a new tab)
  Siddarth Pai

• ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data (opens in a new tab)
  Junhong Shen, Atishay Jain, Zedian Xiao, Ishan Amlekar, Mouad Hadji, Aaron Podolny, Ameet Talwalkar

• Investigating Explainability with a Privacy-Preserving Multi-agent Systems
  Roshni Kaushik, Hyeonsu Kang, Koichi Onoue

• Interactive Debugging and Steering of Multi-Agent AI Systems (opens in a new tab)
  Will Epperson, Gagan Bansal, Victor Dibia, Adam Fourney, Jack Gerrits, Erkang Zhu, Saleema Amershi

• Langroid Research Agent (opens in a new tab)
  Kepler Lang, Kojo Dokyi, Gillis Wang, Yanqi Chen

• VLM-MPC: Model Predictive Controller Augmented Vision Language Model for Autonomous Driving (opens in a new tab)
  Keke Long, Haotian Shi, Jiaxi Liu, Chaowei Xiao, Xiaopeng Li

• HypoVeil: A Privacy-Utility Trade-off Aware Framework for Collaborative Multi-Agent Reasoning
  Hyeonsu B. Kang, Roshni Kaushik, Koichi Onoue

• Agentic Harmonization across Different Frameworks (opens in a new tab)
  Kota Miyake, Miho Tanaka, Koichi Onoue, Graham Neubig

• ToM-based Message Anonymization for Stepwise Confidential-Information Disclosure in Conversation between Agents
  Miho Tanaka, Koichi Onoue, Graham Neubig

• On the Fine-Grained Planning Abilities of VLM Web Agents (opens in a new tab)
  Surgan Jandial, Yinong (Oliver) Wang, Andrea Bajcsy, Fernando De La Torre

Feel free to contact the CMU Agent Workshop organizers (cmu-agent-workshop@andrew.cmu.edu) if you have any questions!