Lin Chen

Real-world professional tasks demand agents that learn from exploration and feedback, a capability unlocked by a novel engine that reconstructs environments to force agents through the full problem-solving lifecycle.

Pretrained visual encoders are a temporary crutch: encoder-free multimodal architectures close the performance gap with encoder-based systems at roughly $10^{22}$ FLOPs, well within current frontier pretraining budgets.

Static textbook circuit problems can now be autonomously transformed into causally grounded, interactive learning environments by coupling multimodal diagram parsing directly with deterministic physics engines.

FACET achieves unprecedented task synthesis quality by preserving source intent and ensuring executable state consistency, leading to more reliable terminal agents.

Executable Blender code transforms text-to-video generation, enabling unprecedented control over scene dynamics and visual fidelity.

LLMs are reshaping urban discovery by fabricating venues and ignoring real ones, leading to significant economic implications for local communities.

LLM agents struggle to juggle multiple tasks when tool use involves realistic delays, revealing critical weaknesses in temporal reasoning and coordination.

Even the best LLMs struggle to effectively discover, refine, and reuse skills over a lifetime of experience, suggesting current benchmarks significantly overestimate real-world agentic capabilities.