Paper Detail
Rima Hazra, Sayan Layek, Somnath Banerjee, Soumen Chakrabarti, Animesh Mukherjee
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 research agents built on proprietary models by up to 3$\times$ recall@50 at roughly a third of the cost.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{hazra2026structurally,
title = {Structurally-bounded Agentic Graph Exploration for Evidence-Grounded Scholarly DeepSearch},
author = {Rima Hazra and Sayan Layek and Somnath Banerjee and Soumen Chakrabarti and Animesh Mukherjee},
year = {2026},
abstract = {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},
url = {https://arxiv.org/abs/2608.24809},
keywords = {cs.CL, cs.IR},
eprint = {2608.24809},
archiveprefix = {arXiv},
}
{}