best-of-n

LLM-as-a-Verifier plugin for DeepSeek Harness (DSH): best-of-N 候选并行生成 + 概率枢轴锦标赛(PPT)验证器择优, 官方样式设置卡片, lav_status/lav_set 会话工具 | DSH 插件: 让 AI 回答经过多候选验证器选优

LLM-as-a-Verifier plugin for DeepSeek Harness — fine-grained reward tools (verify_compare / verify_select / verify_track) with Probabilistic Pivot Tournament, plus a Best-of-N conversation mode with a Web settings panel.

Three-plane probabilistic verifier for DeepSeek Harness: tiered logprob/sample/template judges, seeded tournament best-of-N, layered context reflux.