Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Shuangrui Ding, Xuanlang Dai, Long Xing +14
Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still…
cs.CL2025
ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning
Hongwei Liu, Junnan Liu, Shudong Liu +33
The rapid advancement of Large Language Models (LLMs) has led to performance saturation on many established benchmarks, questioning their ability to distinguish frontier models. Co…