做搜索智能体或 RAG 系统的开发者，Harness-1 的思路能帮你解决模型上下文窗口瓶颈，让智能体在复杂搜索中更高效，值得参考其状态外置设计。
Harness-1 提出一种新方法，将搜索智能体的记忆管理工作从模型中剥离，交给一个外部辅助系统（harness）处理。传统搜索智能体需要在有限的上下文窗口中同时进行搜索决策和记忆所有文档、线索、失败路径等，导致认知负担过重。Harness-1 让模型专注于语义选择（如搜索什么、验证什么），而 harness 负责可恢复状态（如候选池、证据链接、去重观察等）。实验表明，一个 20B 模型通过减少内部记忆负担，在搜索任务上表现显著提升，且在未见过的基准测试上增益更大，说明模型学到了可复用的搜索策略而非领域记忆。
Harness-1 makes search agents better by moving mem…
Harness-1 makes search agents better by moving memory work out of the model and into a helper system.
Shows that intelligence performs better when the environment stops forcing it to spend cognition on bookkeeping.
That search agents should stop using the LLM as the notebook and let a separate harness track the search state.
The paper proved that a 20B model improved search by doing less inside its own head.
The problem is that normal search agents must both think about the next search and remember every document, clue, failed path, and remaining check inside the same limited context.
This formulation puts too much routine state management inside the policy.
Harness-1 separates those jobs.
The model keeps the hard semantic choices: what to search, what to inspect, what to verify, and when the evidence is good enough.
The harness keeps the recoverable state: candidate pools, curated documents, importance tags, evidence links, verification records, deduplicated observations, and budget-aware memory rendering.
That sounds minor until you look at reinforcement learning.
RL works poorly when every failure looks the same, because an empty or wrong final set does not reveal whether the agent searched badly, forgot evidence, skipped verification, or curated carelessly.
By externalizing state, Harness-1 gives the policy a cleaner learning problem: improve decisions over a visible search workspace.
For Harness-1, its gains were larger on held-out benchmarks than on source-family tasks, suggesting the model learned reusable search moves rather than memorized domain habits.
----
Link – arxiv. org/abs/2606.02373
Title: "Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses"