AI RESEARCH
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism
arXiv CS.AI
•
ArXi:2606.00408v1 Announce Type: cross Long-horizon search agents accumulate large amounts of retrieved content across many tool calls, making context-budget efficiency increasingly important. A minimal intervention is to mask stale observations from the context as the trajectory progresses, but it remains unclear when this form of context management helps and why. We study observation masking through a systematic sweep over various agent backbones (4B to 284B parameters) and three retrievers on offline and live-web agentic search benchmarks.