A new arXiv paper studies deep research agents that answer complex questions by repeatedly searching, reading, and reasoning. It argues that the quality of the initial search query is decisive, since well-tuned lexical retrieval can surface useful evidence early on benchmarks like BrowseComp-Plus. The authors frame the opening move as a strategic choice that shapes the rest of the search loop.
A new arXiv paper introduces Mr.LHDR, a benchmark designed to test deep research agents on extended, multi-step tasks. The authors note that current benchmarks mostly measure shorter exploratory work and seldom assess whether agents can keep going over long horizons. It focuses on web search, tool use and combining evidence from multiple modalities.
A new arXiv paper introduces OpenResearcher, a fully open pipeline for generating the long-horizon training data needed by deep research agents, which must interleave search, evidence collection, and multi-step reasoning. The authors note that current data collection approaches depend on proprietary web APIs, which restricts how far such datasets can scale. The work is an updated cross-list submission on arXiv cs.AI.