@article{benchtraceabenchmarkfortestingreflection, title = {BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents}, author = {Jiahao Huang and Fei Cheng and Junfeng Jiang and Zefan Yu and Akiko Aizawa}, year = {2026}, eprint = {2605.29225}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.29225}, }