清华与微软论文提出 HarnessMM，DeepSeek Harness 在 HumanEval 上…
New Tsinghua and Microsoft paper finds that DeepSeek Harness used 87.93% fewer tokens than its original version on 98 HumanEval tasks while success rose from 71
清华与微软的新论文提出 HarnessMM，让模型预先写出后续命令及对应检查条件，工具结果通过检查时直接执行命令、跳过 LLM 调用。在 98 个 HumanEval 任务上，DeepSeek Harness 的 token 用量比原版减少 87.93%，成功率从 71.43% 升至 85.71%；Codex 保持 90.82% 的成功率，token 用量比普通 Codex 减少 29.54%。
推荐理由
AI 评分 54
论文给出 HarnessMM 在 HumanEval 上的 token 节省与成功率变化，可了解智能体跳过冗余 LLM 调用的做法。
主题
正文
New Tsinghua and Microsoft paper finds that DeepSeek Harness used 87.93% fewer tokens than its original version on 98 HumanEval tasks while success rose from 71.43% to 85.71%.
Agent tools like Codex and DeepSeek Harness call the LLM after each tool result to choose the next step. Often that step was already decided, like running tests once the code compiles.
HarnessMM lets the model write future commands with exact arguments, plus a check for each, such as a successful build. When a tool result passes the check, the agent runs the command and skips the LLM call.
On 98 HumanEval tasks, Codex kept its 90.82% success while using 29.54% fewer tokens than plain Codex. DeepSeek Harness rose from 71.43% to 85.71% success and used 87.93% fewer tokens than the original.
If your agent runs predictable chains like write, build, test, have the model plan them once with pass checks instead of re-asking each step.