Gonzalo Gonzalez-Pumariega

gg387@cornell.edu

gonzalo.png

PhD Student

Cornell University

I am a PhD student at Cornell University in the Department of Computer Science. I am advised by Sanjiban Choudhury and work in the PoRTaL lab.

My research is focused on improving LLM capabilities at incorporating feedback, particularly in planning and coding settings. Check out Robotouille which I’ve built to stress test such capabilities.

If you’d like to talk or collaborate, email me! If you are an undergraduate student that wants to work with me, include your interests, how you can contribute, and your resume.

selected publications

  1. mucode.gif
    Multi-Turn Code Generation Through Single-Step Rewards
    Arnav Kumar Jain , Gonzalo Gonzalez-Pumariega, Wayne Chen , and 3 more authors
    2025
  2. robotouille.gif
    Robotouille: An Asynchronous Planning Benchmark for LLM Agents
    Gonzalo Gonzalez-Pumariega, Leong Su Yean , Neha Sunkara , and 1 more author
    In The Thirteenth International Conference on Learning Representations , 2025
  3. llms-for-planning.png
    Query-Efficient Planning with Language Models
    Gonzalo Gonzalez-Pumariega, Wayne Chen , Kushal Kedia , and 1 more author
    2024
  4. apricot_preview.png
    APRICOT: Active Preference Learning and Constraint-Aware Task Planning with LLMs
    Huaxiaoyue Wang , Nathaniel Chin , Gonzalo Gonzalez-Pumariega, and 5 more authors
    In 8th Annual Conference on Robot Learning , 2024
  5. tp_demo.gif
    MOSAIC: Modular Foundation Models for Assistive and Interactive Cooking
    Huaxiaoyue Wang , Kushal Kedia , Juntao Ren , and 14 more authors
    In 8th Annual Conference on Robot Learning , 2024
  6. 2023_demo2code.gif
    Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought
    Huaxiaoyue Wang , Gonzalo Gonzalez-Pumariega, Yash Sharma , and 1 more author
    In Advances in Neural Information Processing Systems 36 (NeurIPS 2023) , 2023