Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism
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. We find that the accuracy gain from masking follows an asymmetric inverted-U shape when plotted against the model's accuracy without context management: a plateau under weak retrievers, a...
| Authors | Haoxiang Zhang, Qixin Xu, Zhuofeng Li et al. |
|---|---|
| Primary category | cs.CL |
| Published | 29 May 2026 |
| Last updated at source | 29 May 2026 |
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.