Xingyao Wang

Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents

How can we assess human-agent interactions? Case studies in software agent design

TOM-SWE: User Mental Modeling For Software Engineering Agents

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Shepherd: Pattern-Guided Trajectory Selection for Coding Agents on SWE-Bench

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

How Do Coding Agents Spend Your Money? Analyzing and Predicting Token Consumptions in Agentic Coding Tasks

OpenHands: An Open Platform for AI Software Developers as Generalist Agents

Advancing LLM Reasoning Generalists with Preference Trees

SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering

Visually Descriptive Language Model for Vector Graphics Reasoning

Training Software Engineering Agents and Verifiers with SWE-Gym