通过执行反馈自动构建和进化智能体运行时框架，提升性能。
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
- 用代数方式组合可复用的框架组件，实现灵活构建。
- 在五个基准上平均提升14.5%（最高达44.0%）。
- 适合关注智能体架构优化与自进化系统的研究者。
智能体性能高度依赖于运行时框架，包括提示词、工具、记忆和控制流等组件，这些组件决定了模型如何观察、推理和行动。然而当前的框架多为手工设计且静态不变：每个新模型或任务仍需定制支撑结构，而执行过程中产生的丰富轨迹也极少被提炼用于系统性改进。我们提出HarnessX，一个可组合、自适应且可演化的智能体框架生成器。HarnessX通过替换代数组装带类型的框架原子单元，利用AEGIS——一种基于符号适应与强化学习之间操作镜像的多智能体演化引擎——实现动态适应，并通过将轨迹转化为框架更新和模型训练信号，闭合框架-模型循环。在五个基准测试（ALFWorld、GAIA、WebShop、tau^3-Bench 和 SWE-bench Verified）中，HarnessX平均提升14.5%（最高达44.0%），且在基线表现较差的任务中增益最大。结果表明，智能体进步不只能靠模型规模扩大；从执行反馈中组合和演化运行时接口，是可行且互补的重要路径。项目主页：https://darwin-agent.github.io/HarnessX/
原文摘要 · Abstract (English)
AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces produced during execution are rarely distilled back into systematic improvement. We introduce HarnessX, a foundry for composable, adaptive, and evolvable agent harnesses. HarnessX assembles typed harness primitives via a substitution algebra, adapts them through AEGIS, a trace-driven multi-agent evolution engine grounded in an operational mirror between symbolic adaptation and reinforcement learning, and closes the harness-model loop by turning trajectories into both harness updates and model training signal. Across five benchmarks (ALFWorld, GAIA, WebShop, tau^3-Bench, and SWE-bench Verified), HarnessX yields an average gain of +14.5% (up to +44.0%), with gains largest where baselines are lowest. These results suggest that agent progress need not come from model scaling alone: composing and evolving runtime interfaces from execution feedback is an actionable and complementary lever. Project homepage: https://darwin-agent.github.io/HarnessX/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。