Junhong Lin
- Papers
- 5
Cite
Notes
Only stored in your browser.
5papers
Authored papers
5Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
arXiv 2026
How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge
arXiv 2026
LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection
arXiv 2025
Reasoning of Large Language Models over Knowledge Graphs with Super-Relations
arXiv 2025
When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmark
arXiv 2024
Affiliations
No known affiliations.
Frequent co-authors
10from 5 papers