7 papers
Atlas: Making Sense of Long Horizon Agent Trajectories
Sangho Suh, Joseph Chee Chang, Pao Siangliulue +5
AI agents can now search literature, generate hypotheses, analyze datasets, and run experiments at a scale difficult for researchers to match. Yet scaling scientific execution does…
Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models
Jiho Lee, Jeongeun Park, Heayoun Choi +2
Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by leveraging rich representations from pretrained vision-language models. However, the…
Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories
Joseph Chee Chang, Michael D'Arcy, Amy X. Zhang +15
A theory draws many independent observations into one framework with novel hypotheses. A researcher building such a theory must synthesize observations scattered across many papers…
Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation
Noy Sternlicht, Simra Shahid, Peter Jansen +3
AI-based ideation systems are often evaluated on the novelty of their ideas, and that judgment is increasingly delegated to large language models. Such judges are typically built a…
DRACULA: Hunting for the Actions Users Want Deep Research Agents to Execute
Nishant Balepur, Malachi Hamada, Varsha Kishore +9
Scientific Deep Research (DR) agents answer user queries by synthesizing research papers into multi-section reports. User feedback can improve their utility, but existing protocols…
LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape
Hita Kambhamettu, Bhavana Dalvi Mishra, Andrew Head +4
Developing a novel research idea is hard. It must be distinct enough from prior work to claim a contribution while also building on it. This requires iteratively reviewing literatu…
Omakase: proactive assistance with actionable suggestions for evolving scientific research projects
Pao Siangliulue, Jonathan Bragg, Doug Downey +2
As AI agents become increasingly capable of complex knowledge tasks, the lack of context limits their capability to proactively reason about a user's latent needs throughout a long…