預測未來行為作為一項學習任務

摘要

對AI系統的信任往往奠基於其運作方式的解釋，人們再據此預測它在面對新輸入時的行為。對於大型推理模型（LRM）而言，這條傳統路徑特別難以遵循：針對單一詞元生成的解釋方法無法自然推廣至長軌跡，而這些軌跡本身若以自然語言解讀，往往也不夠忠實。我們提出一種繞過解釋步驟的替代方案：將行為預測視為可學習的任務，並訓練「行為預測器」——它僅需處理單一推理軌跡，便能做出我們通常期望從解釋中獲得的相同預測。該預測器的訓練數據來自於查詢LRM，無需人類標註，其推論過程則在單次前向傳遞中完成。我們在兩項任務上實例化此方法：預測LRM在重新運行時重複其答案的可能性，以及輸入部分內容的移除如何改變其答案。我們在三個不同的推理數據集上針對這兩項任務評估此方法，結果顯示，經過訓練的行為預測器比GPT-5.4和Claude Opus-4.6以樸素閱讀方式解讀相同軌跡時更為準確，而其推論成本僅為後者的極小部分。我們發現，對骨幹模型進行端到端微調，並從目標LRM初始化，是達到強效表現的必要條件。這些結果表明，推理軌跡包含的關於LRM未來行為的資訊，遠超樸素閱讀所能傳達的內容。

English

Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs. For large reasoning models (LRMs), this conventional route is particularly difficult to follow: explanation methods for single token generations do not naturally generalize to long trajectories, and the trajectories themselves are often not faithful when read as natural language. We propose an alternative that bypasses the explanation step: treat behavior forecasting as a learnable task and train Behavior Forecasters that operates on a single reasoning trajectory to make the same forecasts one would typically seek from an explanation. The forecaster's training data is obtained by querying the LRM with no human annotation, and its inference is done in a single forward pass. We instantiate this approach on two tasks: how likely the LRM is to repeat its answer on re-runs, and how removing parts of the input changes its answer. We evaluate this approach on both tasks across three diverse reasoning datasets and find that trained Behavior Forecasters are more accurate than GPT-5.4 and Claude Opus-4.6 reading the same trajectories as naive readers, at a small fraction of their inference cost. We find that fine-tuning the backbone end-to-end and initializing it from the target LRM are each necessary for strong performance. These results show that the reasoning trajectory carries information about the LRM's future behavior that goes beyond what naive reading conveys.