Invited Talks

Mar 2025: "Building TheAgentCompany: Benchmarking Consequential Real-World Tasks and Adaptive Knowledge Learning" at AAAI 2025 Workshop on Advancing LLM-Based Multi-Agent Collaboration (WMAC25)

Mar 2025: "TheAgentCompany: Benchmarking LLM Agents on Consequential Real-World Tasks" at AAAI Web Agent Revolution Workshop

Mar 2025: "From Workflows to Tools: Building Adaptive Agents On the Fly" at AAAI Web Agent Revolution Workshop

Dec 2024: "From Workflows to Tools: Building Adaptive Agents On the Fly" at Tsinghua University

Nov 2024: "Solving Real-World Tasks via Program Generation" at UIUC iSE Seminar

Sep 2024: "Agent Workflow Memory" at CAMEL-AI

May 2024: "What Are Tools Anyway?" at FLAME (Foundation and LAnguage Model) seminar

Feb 2024: "Tool using, learning, and making with LLMs" at LLM as Agent Seminar

Apr 2023: "Execution-based Open-Domain Coding" at JetBrains Research Team

Tutorials

Jul 2024: "Large Language Models for Tabular Data" at SIGIR 2024

Community Services

Workshop Organization

Feb 2025: Organizer of Deep Learning for Code (DL4C) Workshop at ICLR 2025

May 2024: Head organizer of the first CMU Agent Workshop

Aug 2022: Head organizer of CMU Student Research Symposium

Departmental Services

2024: Member & student representative of CMU LTI DEIB Committee

2024: Chair of Faculty Hiring Student Committee, LTI, CMU

Paper Review

Program committe for NeurIPS, ICLR, ICML; ACL, EMNLP, NAACL, EACL; AAAI

Media Coverage

Sep 2024: MarkTechPost, "Agent Workflow Memory (AWM): An AI Method for Improving the Adaptability and Efficiency of Web Navigation Agents"

Aug 2024: MarkTechPost, "A Reproducible AI Benchmark for Evaluating Program Efficiency via Two Paradigms"

Jul 2023: MarkTechPost, "Google Research Introduces SPAE: An AutoEncoder For Multimodal Generation with Frozen Large Language Models (LLMs)"

Map 2023: SyncedReview, "'May tge Source Be With You' -- BigCode's Open-Access StarCoder Outperforms All Existing Open Code LLMs"