Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision
Sitong Pan, Yipeng Shen, Yilin Lu +3
Reliable web-agent monitoring is difficult when model-internal uncertainty signals such as token logits are unavailable. In this work, we study prefix-level risk prediction for web…
cs.AI2026
SciDER: Scientific Data-centric End-to-end Researcher
Ke Lin, Owais Aijaz, Yilin Lu +3
While large language models accelerate scientific discovery, existing agents face severe limitations in adaptability, domain generalization, and multimodal scalability, often strug…