清华与 Microsoft 论文提出 HarnessMM，用检查机制减少智能体 LLM 调用

AI 导读

清华与 Microsoft 的论文提出 HarnessMM，让模型预先写出后续命令及检查条件，条件通过时直接执行并跳过 LLM 调用。在 98 个 HumanEval 任务上，Codex 保持 90.82% 成功率，同时 token 消耗比普通 Codex 减少 29.54%；DeepSeek Harness 成功率从 71.43% 升至 85.71%，token 消耗比原版减少 87.93%。

正文 · 原文

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.