微任务资格差距：现成SLM何时足以支撑Agent Harness？
原标题：Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?
AI 摘要
该研究构建了一个包含4个agent harness微任务（shell命令自动批准、记忆召回、记忆写入决策、工具选择）的冻结基准，以非LLM基线为锚并采用CI感知的资格规则，测试Qwen3 0.6B-8B和Llama-3.x等现成SLM。结果显示16个（任务×模型）配置无一通过资格阈值，量化到4-bit也不能使任何配置达标，差距更多与模型规模而非精度相关。作者建议将SLM放在满足CI阈值的基线之后，仅在基线不达标处使用SLM，例如4B重排器在BM25候选集上可超过BM25。
正文节选
Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness? Abstract Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-approving shell commands, writing memory, selecting tools, ranking past turns. We ask whether off-the-shelf SLMs meet practitioner-defined thresholds and, when they fail, why, and whether quantization changes the answer. We build a benchmark of