Structurally-bounded Agentic Graph Exploration for Evidence-Grounded Scholarly DeepSearch
cs.CL, cs.IR
Submitted: 2026-08-25
Updated: 2026-08-25
Code: https://github.com/RadiantCrystal/CRASE
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models
- SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
- Measuring Progress on Scalable Oversight for Large Language Models
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- The Semantic Scholar Open Data Platform
- Search-o1: Agentic Search-Enhanced Large Reasoning Models
- Let's Verify Step by Step
- WebGPT: Browser-assisted question-answering with human feedback
- Qwen2.5 Technical Report
- From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agents
- MSciNLI: A Diverse Benchmark for Scientific Natural Language Inference
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering