Andrew Wang

@andrewwnlp

PhD student at @jhuclsp

Pinned
Andrew Wang
@andrewwnlp
Aug 18
New📄: Skill learning helps agents adapt to new domains. What about making agents more cost-efficient as well? We introduce SpeedRunner: the first skill learning paper to make cost a primary optimization target 🧵
00:00
2
Andrew Wang
@andrewwnlp
Apr 20
Excited to share AgentOdyssey! We show that LLM agents still have a long way to go before they achieve human level long-term memory
Brian Zheyuan Zhang
@zheyuanzhang99
Apr 20
Introducing AgentOdyssey — an open-ended, long-horizon text game generation engine for 𝐭𝐞𝐬𝐭-𝐭𝐢𝐦𝐞 𝐜𝐨𝐧𝐭𝐢𝐧𝐮𝐚𝐥 𝐥𝐞𝐚𝐫𝐧𝐢𝐧𝐠 𝐚𝐠𝐞𝐧𝐭𝐬. Real-world agents cannot have a boundary between training and testing: they must learn continuously from interaction with
00:00
1
Andrew Wang
@andrewwnlp
Sep 18, 2025
Tools break in the real world all the time, but not much attention has been given to how well LLMs deal with tool failures. We introduce HOHW, a tool-use benchmark where problems remain solvable even when tools break adversarially.
1
Andrew Wang
@andrewwnlp
Mar 11, 2024
📢 New Preprint: 🤔 Humans often reason using elaborate analogies, but can LLMs do the same? 🧵1/5 We introduce AnaloBench, a benchmark of semantically rich analogies that challenges SOTA LLMs 🤖 📄 arxiv.org/abs/2402.12370
1