SOURCE-LINKED INTELLIGENCE

Structurally-bounded Agentic Graph Exploration for Evidence-Grounded Scholarly DeepSearch

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

We present Crase, a bounded and inspectable alternative to deep research agents for scholarly search. Instead of an open-ended search loop, Crase queries a search engine once for seed papers, expands them along their 1.5-hop citation neighborhood, prunes citation edges whose claims lack entailment support, and ranks the remaining papers with a recency-aware random walk. This makes the candidate set, the reason each paper is kept, and the stopping condition explicit and fixed before inference. On LitSearch and one further benchmarks over a 500K-paper arXiv corpus, Crase outperforms deep researc

Read original source ↗ Open in workspace

recordType

paper

region

Global