HarnessForge：面向自适应智能体系统的联合约束与策略进化

摘要

LLM代理系统被期望在需要不同执行范式的异构任务场景中运行，这对固定代理系统提出了挑战，并促使在孤立组件更新之外进行系统级的元适应。尽管现有工作已对外部框架进行适配或对底层推理策略进行训练，但全系统的适应性仍未得到充分表征。结构与执行之间的适应空间很少被明确化，外部框架与内部推理器之间的兼容性也未得到协同优化。为此，我们提出HarnessForge——一个用于演进LLM代理系统的元自适应框架。HarnessForge将代理系统形式化为"框架-策略"对，定义了稳定的适应空间，将框架层的执行结构与策略层的推理行为分离。随后，它通过故障引导的框架剪裁和框架条件化的策略对齐，实现框架与策略的协同进化。在涵盖不同领域的五个基准实验表明，HarnessForge持续提升了Qwen3-4B和Qwen3-8B骨干模型的表现，优于仅优化框架或仅优化策略的基线方法，相比最强基线获得了最高12.0%的性能提升，并实现了优越的 rollout-效率权衡，证明了框架与策略的协同进化是有效的，且框架与推理策略之间的可执行兼容性对于代理系统的适应至关重要。代码已开源：https://github.com/mingju-c/HarnessForge

English

LLM agents are increasingly expected to operate across heterogeneous task regimes that require distinct execution paradigms. This challenges fixed agent systems and motivates system-level meta-adaptation beyond isolated component updates. While existing works have adapted external harness or trained underlying reasoning policies, full-system adaptation remains insufficiently characterized. The adaptation space between structure and execution is rarely made explicit, and the compatibility between the external harness and the internal reasoner is not optimized jointly. We propose HarnessForge, a meta-adaptive framework for evolving LLM agent systems. HarnessForge formulates an agent system as a harness--policy pair, defining a stable adaptation space that separates harness-level execution structure from policy-level reasoning behavior. It then performs harness--policy co-evolution through fault-guided harness tailoring and harness-conditioned policy alignment. Experiments across five benchmarks from diverse domains show that HarnessForge consistently improves both Qwen3-4B and Qwen3-8B backbones, outperforming harness-only and policy-only baselines with gains of up to 12.0\% over the strongest baseline and achieving favorable rollout-efficiency tradeoffs, demonstrating that harness--policy co-evolution is effective, and that executable compatibility between the harness and reasoning policy is essential for agent-system adaptation. The code is available at https://github.com/mingju-c/HarnessForge.