3 papers
cs.AI2026
Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift
Dan C. Hsu, Luke Lu
Deployed LLM agents rely on agentic context, the model-external textual control content assembled by an operational harness. In this work, the mutable component of that context is…
cs.AI2026
Evaluating Generative Agents with Actions Grounded in Socially Distributed Task Environments using Incognita
Dan C. Hsu, Luke Lu
Effective agency in social environments depends on when an agent seeks knowledge, when it acts, and whether its actions are justified by acquired information. Existing grounded ben…
cs.LG2026
Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback
Ved Sriraman, Peihan Liu, Daniel Hsu +1
Imitation Learning is a natural framework for learning in sequential decision-making systems and has emerged as the dominant paradigm through which we understand language model tra…