Zora Wang (@ZhiruoW) / X

Zora Wang

427 posts

Zora Wang

@ZhiruoW

PhD student @LTIatCMU @CMU_SCS | fun 👩🏻‍💻 🐈 💃 🪴 🎶

Pittsburgh, PA

Joined August 2021

Pinned
Zora Wang
@ZhiruoW
May 19
Excited to announce our tutorial: "Future of Work in the Age of LLMs" at #ACL2026 in San Diego, July 2! 🌴 There's a lot of speculation about AI and the future of human work. Our tutorial unpacks it from four angles: → The landscape of human work → How to build LLMs to augment
17K
Zora Wang
@ZhiruoW
Oct 24, 2025
🎉Thrilled to be named a Google PhD Fellow! Feeling incredibly grateful for my advisors, collaborators, and friends who’ve supported and inspired me along the way 🫶 Looking forward to the journey ahead!
Google.org
@Googleorg
Oct 23, 2025
🎉 We're excited to announce the 2025 Google PhD Fellows! @Googleorg is providing over $10 million to support 255 PhD students across 35 countries, fostering the next generation of research talent to strengthen the global scientific landscape. Read more: goo.gle/43wJWw8
96K
Zora Wang
@ZhiruoW
Nov 15, 2023
Everyone is using RAG, but most of the retrieved context is noisy! 🚨 Introducing FilCo: “Learning to Filter Context for Retrieval-Augmented Generation” TL;DR: Get rid of the irrelevant content using FilCo, and you'll get better outputs. Preprint: arxiv.org/abs/2311.08377
51K
Zora Wang
@ZhiruoW
Sep 12, 2024
How can we create AI agents that continually improve, learning from past successes? Presenting 🌟Agent Workflow Memory🌟, which allows agents to induce, learn, and use task workflows from experiences on the fly🪽 Adding AWM to a strong agent improves accuracy by 51.1% on
39K
Zora Wang
@ZhiruoW
Oct 28, 2025
Agents are joining us at work -- coding, writing, design. But how do they actually work, especially compared to humans? Their workflows tell a different story: They code everything, slow down human flows, and deliver low-quality work fast. Yet when teamed with humans, they shine
00:00
94K
Zora Wang
@ZhiruoW
Mar 20, 2024
Tools can empower LMs to solve many tasks. But what are tools anyway? github.com/zorazrw/awesom… Our survey studies tools for LLM agents w/ –A formal def. of tools –Methods/scenarios to use&make tools –Issues in testbeds and eval metrics –Empirical analysis of cost-gain trade-off
69K
Zora Wang
@ZhiruoW
Apr 15, 2025
Meet ASI: Agent Skill Induction A framework for online programmatic skill learning — no offline data, no training. 🧠 Build reusable skills during test 📈 +23.5% success, +15.3% efficiency 🌐 Scales to long-horizon tasks, transfers across websites Let's dive in! 🧵
26K
Zora Wang
@ZhiruoW
Jul 14, 2024
I will give a tutorial about "LLM for Tabular Data" at @SIGIRConf from 9-12:30 today, together with @HaoyuDong9, my previous mentor at Microsft Research, Asia! Join our tutorial in person, or check our slides/recording online if you're interested! llm4table-tutorial.github.io
13K
Zora Wang
@ZhiruoW
Jun 21, 2024
Introducing 🔥CodeRAG-Bench🔥 a benchmark for retrieval-augmented code generation! 🔗arxiv.org/abs/2406.14497 - Supports 8 codegen tasks and 5 retrieval sources - Canonical document annotation for all coding problems - Robust evaluation of retrieval and end-to-end execution
GIF
37K
Zora Wang
@ZhiruoW
Oct 8, 2025
so grateful for my advisors today 🥹🫶🚀
Huan Sun
@hhsun1
Oct 7, 2025
How often do you see two professors (from CMU) to jointly present their poster? @gneubig @dan_fried A must-check! 😆😆😆
18K
Zora Wang
@ZhiruoW
Dec 1, 2023
Heading to #EMNLP2023 next week ✈️ If you’re interested in Code Generation🧑‍💻don't hesitate to check out our two papers! - ODEX, A challenging benchmark with open-domain coding queries: arxiv.org/pdf/2212.10481… - API-assisted code generation for tableQA: arxiv.org/pdf/2310.14687…
23K
Zora Wang
@ZhiruoW
Jul 8, 2025
ASI is now accepted to @COLM_conf #COLM2025! 🍁 🔗
Zora Wang
@ZhiruoW
Apr 15, 2025
Meet ASI: Agent Skill Induction A framework for online programmatic skill learning — no offline data, no training. 🧠 Build reusable skills during test 📈 +23.5% success, +15.3% efficiency 🌐 Scales to long-horizon tasks, transfers across websites Let's dive in! 🧵
arxiv.org
Inducing Programmatic Skills for Agentic Tasks
To succeed in common digital tasks such as web navigation, agents must carry out a variety of specialized tasks such as searching for products or planning a travel route. To tackle these tasks,...
7.1K
Zora Wang
@ZhiruoW
Apr 22, 2025
Couldn't agree more on agent "continually adapt" from "streamed experiences"! This is exactly what we've envisioned in building online adaptive agents with self-induced evolving memory & skills in AWM (arxiv.org/abs/2409.07429) and ASI (arxiv.org/abs/2504.06821)! Yet still some
Richard Sutton
@RichardSSutton
Apr 11, 2025
David Silver really hits it out of the park in this podcast. The paper "Welcome to the Era of Experience" is here: goo.gle/3EiRKIH.
arxiv.org
Agent Workflow Memory
Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In...
10K
Zora Wang
@ZhiruoW
Jan 24, 2024
Do you find LM-written programs too complex to understand? Do bugs often pop up in these solutions? Check out *TroVE*, a training-free method to create accurate, concise, and verifiable solutions by inducing tools 🔗: arxiv.org/pdf/2401.12869…
00:00
23K