Hello there! I’m Ke Yang (杨可), currently a fourth-year Ph.D. at UIUC under the guidance of Professor ChengXiang Zhai. I obtained my bachelor’s degree from Tsinghua University. I previously interned at Amazon AWS, the Deep Learning Group at Microsoft Research, and Google.
I work on AI agents, language models, information retrieval, and multimodality foundation models (of top interest). I’m also keen on resolving AI bias and discrimination. Always open to collaboration — feel free to get in touch!
News
| Sep 2026 | New preprint: StudentSim: Training LLM-based Student Simulators — personalized LLM-based student simulators trained from sparse learner records, evaluated by whether they match student responses and change reliably after AI tutor guidance. Project site.  |
|---|---|
| Jun 2026 | Joined Google as a Student Researcher this summer.  |
| Feb 2026 | New preprint: PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents — a plug-and-play memory module that turns raw agent experience into reusable knowledge and consistently improves long-horizon decision-making. Code on GitHub.  |
| May 2025 | New preprint: Ten Principles of AI Agent Economics — my first perspective paper, reflecting on AI agent incentives and what they imply for the broader economy.  |
| May 2025 | New preprint on benchmarking Just-in-time Information Recommendation — AI assistants that proactively recommend the right information at the right time.  |
Selected Publications
-
PlugMem: A Task-Agnostic Plugin Memory Module for LLM AgentsICML 2026 In International Conference on Machine Learning (ICML)TL;DR PlugMem serves as a task-agnostic plug-and-play memory module for LLM agents that turns raw experience into reusable knowledge, helping agents remember what matters, not everything. -
Ten Principles of AI Agent EconomicsarXiv 2025TL;DR We propose ten principles of AI agent economics, offering a framework to understand how AI agents make decisions, influence social interactions, and participate in the broader economy. -
AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web AgentsICLR 2025 In International Conference on Learning Representations (ICLR)TL;DR AgentOccam surpasses the previous state-of-the-art and concurrent LLM-based web agent with its observation and action space alignment. We achieve this without using in-context examples, new agent roles, online feedback or search strategies. -
Tiny Minds, Smaller Worlds: Training and Evaluating Tiny Language Models in a Simpler Language EnvironmentarXiv 2025TL;DR We train and evaluate tiny language models using a text dataset with simplified vocabularies and linguistic structures, mimicking how children learn language through simplified environments as part of their initial curriculum. -
Bias and Volatility: A Statistical Framework for Evaluating Large Language Model’s Stereotypes and the Associated Generation InconsistencyNeurIPS 2024 D&B Track In Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks TrackTL;DR Bias-Volatility Framework measures discrimination in models by considering both their consistently biased preference and preference variation across contexts. -
If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent AgentsICLR Workshop 2024 In ICLR Workshop on Large Language Model (LLM) AgentsTL;DR The Wizard survey explores the synergy between code and large language models (LLMs), highlighting how code empowers LLMs and benefits LLMs when they serve as intelligent agents. We emphasize code’s readability, symbolic abstraction, and graph structure, presenting it as a valuable component in LLMs’ training corpus. -
ADEPT: A DEbiasing PrompT FrameworkAAAI 2023 In Proceedings of the AAAI Conference on Artificial IntelligenceTL;DR ADEPT introduces a novel debiasing loss function based on counterfactual bias and manifold learning insights. "Prompt" here refers to prompt-tuning (peft) rather than prompt-engineering.
