DarwinX：透過自然選擇演化智能體框架

摘要

LLM 智能體的能力不僅取決於模型權重，還取決於其框架：提示詞、工具、技能與控制流。自我改進迴圈已經在編輯框架，但單一譜系搜尋具有路徑依賴性，且局部勝利常使其他任務退化。我們提出 DarwinX，將自我演化視為在模型凍結條件下對框架群體進行選擇：「保留並擴展」契約只接納能擴展覆蓋範圍且不造成退化的變體；檔案庫保存替代譜系以供重組；來自失敗、教師與自我產生的證據共享同一個編輯介面。適應度來自每個基準測試自身的驗證器：無需標準解答，無需人工挑選獲勝者。在四個逐步將演化訊號與測試分離的基準測試上，單一迴圈平均增加約 17 個百分點：Terminal-Bench 2.1 在匹配的基礎模型上提升 +7.7 至 83.2%，在更強的基礎模型上達到 84.7% 的驗證前沿；TerminalWorld 的保留測試分區達到 68.3%，領先所有現成智能體；WebArena-Infinity 真實任務 pass@1 從 43.5% 提升至 93.0%（經審計無誤）；且 Terminal-Bench 2.1 的框架可不經修改地遷移至 SWE-bench Verified。演化出的是通用智能體能力，而非針對特定基準測試的補丁，因此它能經受任務、驗證器與基礎模型的改變。凍結的模型不必是固定的智能體：框架選擇能將評估計算轉化為持久能力。

English

An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow. Self-improvement loops already edit harnesses, yet single-lineage search is path-dependent and local wins often regress other tasks. We introduce DarwinX, which treats self-evolution as selection over a population of harnesses with the model frozen: a preserve-and-extend contract admits only variants that extend coverage without regressing, an archive keeps alternative lineages for recombination, and failure-, teacher-, and self-derived evidence share one edit interface. Fitness comes from each benchmark's own verifier: no gold solutions, no hand-picked winners. Across four benchmarks that progressively separate the evolution signal from the test, one loop adds about 17 points on average: Terminal-Bench 2.1 rises +7.7 to 83.2% on a matched base and to the verified frontier at 84.7% on a stronger one; TerminalWorld's held-out split reaches 68.3%, ahead of every off-the-shelf agent; WebArena-Infinity real-task pass@1 rises from 43.5% to 93.0% audit-clean; and a Terminal-Bench 2.1 harness transfers unchanged to SWE-bench Verified. What evolves is general agent competence, not benchmark-specific patches, so it survives changes of task, verifier, and base model. A frozen model need not be a fixed agent: harness selection turns evaluation compute into durable capability.