Benchmarks are essential for evaluating and improving large language models (LLMs). Yet many widely used benchmarks are redundant, making evaluation unnecessarily expensive. Benchmark compression lowers this cost by estimating full-benchmark scores and rankings from a partial evaluation. Research in this area has grown...
Guo-Ming Ling, Yupei Lin, Zhong-Zhan Huang et al.· 0 citations
Scientific coding agents receive equations, boundary conditions, and output requirements in writing, then must assess the programs they revise. Rules to Tools (R2T) supplies prepared executable checks of public scientific requirements. Matched SciCode repair groups share written checks, starting programs, model, and bu...
Jing-Jie Ning, Guo-Jiang Zhao, Cheng-Xin Xu et al.· 0 citations
This work presents ZipBench, a simple and low-cost BCM with theoretical error and rank-consistency guarantees that reduces the cost of both LLM evaluation and compact benchmark construction, lowering the barrier to broad LLM research for compute-constrained researchers.
Zhong-Zhan Huang, Jun-Xin Li, Guo-Ming Ling et al.· 0 citations
The Discovery Certification Protocol (DCP) turns an outcome claim into an executable audit under a registered model, information boundary, and budget, and a deterministic verifier reproduces these local decisions from frozen records.
Jing-Jie Ning, Shan Zhong, Xiao-Chuan Li et al.· 1 citation
By validating decisions rather than only artifacts, this design turns adaptive search into reusable evidence wherever agents propose executable alternatives against a fixed evaluator.
