擴展智能體資料以實現長時程終端智能

摘要

終端機代理正從本機操作邁向完成真實世界的專業任務。短軌跡能展示指令與工具呼叫，但無法完整呈現代理如何透過探索累積證據、用證據輔助判斷、根據回饋持續調整策略，以及將中間結果轉化為最終交付成果。高品質的長時程軌跡會在單一問題解決過程中捕捉這些代理行為模式及其關聯，為持續自主工作提供更豐富的經驗。然而，環境合成可能會事先完成或簡化這些模式背後的關鍵工作，因而移除代理原本應進行的探索、實作與驗證需求。為解決此問題，我們提出 TerminalHorizon，一套專為長時程終端機代理設計的全自動資料合成引擎。它從真實世界專業工作出發，利用獨立執行來識別建構過程中遺漏的關鍵工作，並利用所產生的證據引導環境重建。為了將這些模式延伸至各階段，它會在同一目標下逐步擴展任務，引入以先前結果為基礎、且需要進一步探索與改進的新需求。使用此引擎，我們建構 1.5K 個任務環境，並在產生的資料集上對 Qwen3.5-27B 進行監督式微調，以得到 TerminalHorizon-27B。我們在涵蓋程式設計代理任務、真實世界生產環境中的代理任務，以及一般推理的所有 12 個基準測試上，取得大幅效能提升。多個 RSI 案例研究，每項都有 12 小時研究預算，進一步證明該模型能在初始解決方案之外持續實驗、根據回饋改進其方法，並在最終交付成果中保留有效的改進。

English

Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool calls, but they do not fully show how agents accumulate evidence through exploration, use it to inform judgments, continually adjust strategies based on feedback, and turn intermediate results into final deliverables. High-quality long-horizon trajectories capture these agentic behavioral patterns and their connections within a single problem-solving process, providing richer experience for sustained autonomous work. However, environment synthesis may complete or simplify the key work underlying these patterns in advance and thus remove the need for exploration, implementation, and verification that the agent was meant to perform. To address this, we introduce TerminalHorizon, a fully automated data synthesis engine for long-horizon terminal agents. Starting from real-world professional work, it uses independent execution to identify key work omitted during construction and uses the resulting evidence to guide environment reconstruction. To extend these patterns across stages, it progressively expands tasks under the same goal, introducing new requirements that build on prior results and call for further exploration and improvement. Using this engine, we construct 1.5K task environments and perform supervised fine-tuning of Qwen3.5-27B on the resulting dataset to obtain TerminalHorizon-27B. We achieve substantial performance gains on all 12 benchmarks spanning coding-agent tasks, agentic tasks in real-world production settings, and general reasoning. Multiple RSI case studies, each with a 12-hour research budget, further demonstrate the model's ability to continue experimenting beyond an initial solution, improve its methods based on feedback, and retain effective improvements in its final deliverables.

擴展智能體資料以實現長時程終端智能

Scaling Agentic Data for Long-Horizon Terminal Intelligence

摘要

Support