Research
BrowseComp went from 30% → 90% in 10 months. Search-agent benchmarks are saturating. So we built Lo…
美团LongCat发布LoHoSearch：更难搜索智能体基准
Meituan LongCat (@Meituan_LongCat)
X (formerly Twitter)BrowseComp went from 30% → 90% in 10 months. Search-agent benchmarks are saturating. So we built LoHoSearch: a harder benchmark for search agents, with questions automatically generated from a 7.62M-entity Wikipedia knowledge graph instead of written by humans. It maximizes
Open sourceRecommended because
This is worth tracking because it is a concrete research signal, not just a passing headline. The source preview points to a research result, method, evaluation, dataset, or safety finding. For builders and operators, "BrowseComp went from 30% → 90% in 10 months. Search-agent benchmarks are saturating. So we built Lo…" can be used as a checkpoint for technical due diligence, roadmap bets, agent design, and evaluation strategy. I keep this thread indexed so future searches around AI research papers, technical methods, and applied AI systems can land on a source-linked page instead of disappearing into a fast-moving feed from X (formerly Twitter).
What to take from this signal
Context
"BrowseComp went from 30% → 90% in 10 months. Search-agent benchmarks are saturating. So we built Lo…" is archived here as a source-linked AI signal from X (formerly Twitter). The useful part is the connection between BrowseComp, went, months, Search-agent, benchmarks and technical due diligence, roadmap bets, agent design, and evaluation strategy, which makes the item more actionable than a normal feed headline. The source context says: BrowseComp went from 30% → 90% in 10 months. Search-agent benchmarks are saturating. So we built LoHoSearch: a harder benchmark for search agents, with questions automatically generated from a 7.62M-entity Wikipedia knowledge graph instead of written by humans. It maximizes
Builder takeaway
For an AI builder, the main takeaway is to watch how this signal changes practical decisions around technical feasibility, evaluation design, safety limits, and product primitives. It can inform what to test next, which product surface to compare, and whether the underlying workflow is ready for real users.
Source context
X (formerly Twitter) remains the authoritative source for the original claim. This page adds a stable archive URL, a short builder interpretation, and related search language so the item can be found later when the original feed has moved on.
Search angles
- BrowseComp went from 30% → 90% in 10 months. Search-agent benchmarks are saturating. So we built Lo… Research context
- X (formerly Twitter) AI research
- BrowseComp, went, months, Search-agent, benchmarks builder takeaway
- AI research papers, technical methods, and applied AI systems
This page keeps a source preview and a stable archive URL for search discovery. The original source remains authoritative.