用开源小语言模型测量医患共享决策，精准评估隐私与可持续性优势。
arXiv:2607.06127v1 Announce Type: new Abstract: We present LLM4SDM, the first study of open-source smaller language models (OS-sLLMs) for automated as…
用小代理模型精准预测LLM推理性能，省钱省算力的高效新方案。
arXiv:2509.21013v4 Announce Type: replace-cross Abstract: Given the prohibitive cost of pre-training large language models, it is essential to leverag…
微博3B小模型VibeThinker-3B逆袭Google大模型，用新测试策略引发AI基准再争论。
On Sunday, a team of nine researchers at Sina Weibo — the Chinese social media giant better known for its microblogging platform than for cutting-edge…
用 POLARIS 引导小模型写出连贯长故事，突破规模限制，让轻量模型也能驾驭长篇叙事
arXiv:2606.04095v1 Announce Type: cross Abstract: Small open-weight models struggle at long-form creative writing: their generated stories either fall…
小模型天然具备策略级探索优势，在GRPO中提升多样性比传统token随机更稳定高效
arXiv:2605.30789v1 Announce Type: cross Abstract: We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (G…
本地运行大模型调度小模型，告别高昂API成本，实现高效工具调用
Article URL: https://github.com/district-solutions/open-agent-tools-coder Comments URL: https://news.ycombinator.com/item?id=48307438 Points: 9 # Comm…
提出Token级LLM协作新方法FusionRoute，突破领域模型融合粒度，让小模型协同超越大模型。
arXiv:2601.05106v4 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strengths across diverse domains. However, achieving st…
用小型开源模型生成动态建议，巧妙引导黑盒大模型提升输出质量，无需修改权重。
arXiv:2510.02453v3 Announce Type: replace-cross Abstract: Frontier language models are deployed as black-box services, where model weights cannot be m…