HarnessX：一個可組合、自適應及可演化的代理框架工廠

摘要

AI智能體的效能關鍵取決於運行時框架，該框架包含提示、工具、記憶以及控制流程，這些元素調節著模型如何觀察、推理和行動。然而，當今的框架大多仍依賴手工設計且靜態：每個新模型或新任務仍需定制化的支撐結構，而執行過程中產生的豐富軌跡鮮少被提煉為系統性的改進。我們提出 HarnessX，一個用於可組合、自適應和可演化的智能體框架的打造平台。HarnessX 通過替換代數組裝類型化框架原語，通過 AEGIS（一個基於軌跡的多智能體演化引擎，其基礎是符號適應與強化學習之間的運作映射）進行自適應，並通過將軌跡轉化為框架更新和模型訓練信號來閉合框架-模型循環。在五個基準測試（ALFWorld、GAIA、WebShop、tau^3-Bench 和 SWE-bench Verified）中，HarnessX 平均提升了 +14.5%（最高 +44.0%），在基線最低的測試中提升最大。這些結果表明，智能體的進步不必僅來自模型規模擴展：從執行反饋中組合和演化運行時接口是一個可操作且互補的槓桿。完整的程式碼庫將在未來版本中開源。

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. The complete codebase will be open-sourced in a future release.