Profile Picture

Zora (Zhiruo) Wang

ηŽ‹θŠ·θ‹₯

PhD Student

Carnegie Mellon University

Language Technologies Institute

About Me

I am currently a PhD student at the Language Technologies Institute at Carnegie Mellon University working with Daniel Fried and Graham Neubig. My primary research interest is to use programmatic approaches to solve real-world tasks. Particularly, I am working on:

Memory- and Skill-Adaptive Agents
  1. Digital agents that learns navigation workflows in memory [AWM] and specialized skills as actuators [ASI] [SkillWeaver]; build verifiable and efficient toolboxes for math, data analysis, and visual reasoning tasks [TroVE]
  2. These agents often facilitate human verification [TroVE] and improves task success [CowPilot]
  3. On versatile tasks such as presentation making [AutoPresent], software engineering [ODEX], and popular professions [TAC]
Augmented Language Models
  1. Tools [Survey]: designed by human experts [AutoPresent] or LMs [TroVE]; their behaviors to under-specified queries and execution failures [Fail-TaLMs]
  2. Programs: Challenging benchmarks for open domain [ODEX], multilingual [MCoNaLa], and data science [HiTab] problems; Performant code LMs [StarCoder] [ECCO] with [Code RAG], assistive [APIs], and libraries in [DocPrompting]
  3. Knowledge: retrieve texts [FilCo] [ReAtt] [RAGGED] and structured data [WikiTable] [TUTA]

News

🐾 Older News
  • Jan 2025: Check out the podcast episode about interesting discussions✨ around "Agent Workflow Memory" [link]
  • Dec 2024: Gave a talk at Tsinghua University about "From Workflows to Tools: Building Adaptive Agents On the Fly" (slides)
  • Nov 2024: Gave a talk at UIUC iSE Seminar about "Solving Real-World Tasks via Program Generation". Feel free to check out my slides here.
  • Oct 2024: Joined the panelist of Our CS (Workshop for Undergraduates in CS) and shared some of my thoughts about research
  • Sep 2024: Gave an invited talk at Camel-AI πŸͺ about Agent Workflow Memory, check out the video, paper, and tweet
  • Jul 2024: Gave a tutorial at SIGIR about Large Language Models for Tabular Data, check out the slides & recordings if you're interested!
  • May 2024: Organized our CMU Agent Workshop πŸ€– with plenty of events -- insightful tutorials, talks, and posters! I also gave two (short) tutorials about tool-augmented LMs and codegen testbeds.
  • Mar 2024: Gave a guest lecture about "Language Agents and Tool Use" at the Advanced NLP course (11-711) course, check out the recordings!
  • Mar 2024: Gave a talk at the [FLAME_ (Foundation and LAnguage Model) πŸ”₯] seminar, about [our recent survey] and [TroVE]
  • Feb 2024: Gave a talk about Language Models with Tools at the LLM as Agent Seminar, about [TroVE] and works in progress 🀫
  • Feb 2024: Gave a lecture about Evaluation (metrics and benchmarks) for the Neural Code Generation (11-891) course πŸ’»
  • Jan 2024: TAing for the new course [11-891 Neural Code Generation], reach out if you want to discuss more project ideas πŸͺ„
  • Nov 2023: Gave a guest lecture about Evaluation and Benchmarks for Code Generation for the Advanced NLP course (11-711) πŸ‘©β€πŸ« more details [here]
  • Aug 2023: A talk about πŸ› οΈ Tool using, learning, and making with LLMs at Code Generation Reading Group, check out the [video]
  • Apr 2023: Gave a talk about [ODEX] at the Machine Learning Methods in Software Engineering (video) hosted by JetBrains Research Team πŸ‘©β€πŸ’»

    • Upcoming Events

    My Recent Favorite Publications

    Agent Skill Induction

    Agent Skill Induction

    Agent Workflow Memory

    Agent Workflow Memory

    Survey on Language Models

    What Are Tools Anyway? A Survey from the Language Model Perspective

    TroVE Took Making

    TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks

    Get Connected

    If you want to get connected, discuss potential project ideas, ask about CMU application, or chat about any other relevant topics, my office hours are available every Friday 4-5 pm EST. Email me to secure a time to chat!

    I often mentor a small number of students every semester, please fill out this application form if you're interested in working with me! However, as I got plenty of emails, I might not be able to reply to all of them.

    If you are from underrepresented groups, or do not have much research experience, you are encouraged to reach out!