1
Fractured Chain-of-Thought Reasoning
一篇最新论文探索了思维链推理中的“断裂”现象，揭示了大模型推理过程中的关键缺陷与改进方向。
arXiv:2505.12992v4 Announce Type: replace-cross Abstract: Inference-time scaling techniques have significantly bolstered the reasoning capabilities of…
2
Robust Reasoning Benchmark
AIME 2024数学题经13种文本扰动，测试大模型推理鲁棒性，揭示依赖格式的短板
arXiv:2604.08571v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) achieve high performance on standard mathematical benchma…
3
Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs
自动驾驶VLA模型在传感器扰动下推理脆弱性被揭穿，最新论文揭示其可靠性隐患
arXiv:2605.21446v1 Announce Type: cross Abstract: Interpretable autonomous driving planners depend not only on generating explanations, but also on th…