2025 Summer

2025 Summer Schedule

We are excited to welcome a large group of high school researchers to our summer research on agents and reasoning.

• • Git Repo: github.com/philmui/research2025

  • Summer Projects

    • Project Proposal Template: [link]

    • Spreadsheet of Summer Projects: [link]

• Jun 21: Introduction to summer research

  • Repo: [github]

  • Recording: [video]

  • Readings:

    • Philippe Laban, et al.  LLMs Get Lost In Multi-Turn Conversation,  arXiv:2505.06120.  [link]

    • Prateek Chhikara, et al.  Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory,  arXiv:2504.19413. [link]

• Jun 28: Memory & Reasoning

  • Repo: [github]

  • Recording: [video]

  • Readings:

    • D. Wu, et al.  LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory.  arXiv:2410.10813. [link]

• July 5: MemAgents

  • Repo: [github]

    • SummaryAgent: [link]

    • ReductiveAgent: [link]

  • Recording: [video]

  • Readings:

    • Zikai Xie.  Order Matters in Hallucination: Reasoning Order as Benchmark and Reflexive Prompting for Large-Language-Models, arXiv:2408.05093.  [link]

    • Liam Barkley, et al.  Investigating the Role of Prompting and External Tools in Hallucination Rates of Large Language Models, arXiv:2410.19385 [link]

• July 12: BioReasoning

  • Repo: [github]

  • Recording: [video]

  • Readings:

    • Pascal J. Sager, et al. A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions,  arXiv:2501.16150, June 2025. [link]

• July 19: Agent Optimization

  • Recording: [video]

  • Readings:

    • Han Zhou, et al. Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies, arXiv:2502.02533, February, 2025 [link]

• July 26: Project Checkin

  • Recording: [video]

  • Readings

    • Proportional Representation (PR) Library: Types of Voting Systems [link]

    • Stephan Zheng, Alexander Trott, Sunil Srinivasa, David C. Parkes, Richard Socher.  The AI Economist: Optimal Economic Policy Design via Two-level Deep Reinforcement Learning, arXiv:2108.02755. [link]

• August 2: Prompt Optimization

  • Recording: [video]

  • Github: [promptomatrix]

  • Adrian Gamarra Lafuente (Stanford) on Agent Optimization

  • Readings

    • A. Gamarra Lafuente. Archon:An Architecture Search Framework for Inference-Time Techniques. arXiv:2409.15254, September, 2024. [link]

    • Omar Khattab, et al.  DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines.  arXiv:2310.03714, October, 2023. [link]

    •  Rithesh Murthy, et al.  Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models, arXiv:2507.14241, August, 2025. [link]

• August 9: Deep Research 

  • Recording: [video]

  • Satyajit Kumar (UCLA) on Deep Research Mode

  • SCCUR Conference

    • https://www.sccur.org/

  • Readings:

    • Yuxang Huang, et al.  Deep Research Agents: A Systematic Examination And Roadmap.  arXiv:2506.18096, June 22, 2025. [link]

• August 16: Memory Evaluation & Blitz Talks

  • Recording

  • Andrew Goldberg (UC Berkeley) research on agentic memories & evaluations

  • ASDRP Blitz Talks [abstracts]

• August 23: Final Summer Session

  • Recording

  • SCCUR Abstracts  [abstracts]