Publications
2026
-
Back to Basics: A Skill-Centric Approach to Generalist Web AgentsIn Preprint, 2026 -
READ: What Makes a Pretrained VLA Teachable by Demonstration?In CoRL 2026 Workshops: Pretrain to Adapt and RoboMem, 2026 -
Teaching Agents in their Own Style: Blackbox Teacher Distillation for Web AgentsIn Preprint, 2026 -
Don’t Retrain, Remix: Adaptation of Web Agents using Mixture HypernetworksIn Preprint, 2026 -
DERELAB: Probing Defeasible Reasoning and Confirmation Bias in LLMs with a Generative BenchmarkIn EMNLP, 2026 -
Language-Critique Imitation Learning from Suboptimal DemonstrationsIn CoRL 2026 Workshops: Oops, I Erred and Learning from Corrections and Interventions, 2026 -
DORA Explorer: Improving the Exploration Ability of LLMs Without TrainingIn Submission, 2026 -
The Hard Part Comes After Search: Benchmarking Web Agents on Synthesizing, Organizing, and Displaying KnowledgeIn Findings of EMNLP, 2026 -
-
2025
-
-
Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?In COLM, 2025 -
Efficient Exploration and Discriminative World Model Learning with an Object-Centric AbstractionIn ICLR, 2025
2024
-
VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of ThoughtIn NeurIPS, 2024