多分享，少搜尋：協作平行思考以實現高效的測試時間擴展

摘要

測試時擴展（TTS）透過分配額外的推論計算資源來探索解空間，從而增強大型語言模型的推理能力。然而，現有的平行TTS方法通常在搜索過程中保持分支隔離：中間發現仍為分支私有，無法即時指引其他分支。這種資訊隔離導致大量的冗餘探索，因為分支會重複發現其他地方已有的資訊，並且需要更多的搜索步驟來收集達到正確答案所需的完整決策資訊。為了解決這個問題，我們提出協作平行思考（CPT），一個無需訓練的推論框架，能夠在搜索過程中實現平行分支間的資訊共享。CPT 從正在進行的分支中提取精簡的中間資訊，維護一個去重的查詢級資訊池，並透過輸入上下文廣播池條目，使得後續搜索步驟中的每個分支能夠重用其他分支的發現，而非重新發現相同的資訊。實證上，在 HMMT 和 AIME 基準上的實驗表明，CPT 在各種推展預算和模型規模上建立了比強基線更強的準確率-延遲帕累托前沿，凸顯了搜索時協作作為高效平行 TTS 的有效方向。

English

Test-Time Scaling (TTS) enhances the reasoning capabilities of large language models by allocating additional inference compute to explore the solution space. However, existing parallel TTS methods typically keep branches isolated during search: intermediate discoveries remain branch-private and cannot guide other branches in time. This information isolation causes substantial redundant exploration, as branches repeatedly rediscover information already found elsewhere and require more search steps to collect complete decision information needed to reach correct answers. To bridge this gap, we propose Collaborative Parallel Thinking (CPT), a training-free inference framework that enables search-time information sharing across parallel branches. CPT extracts compact intermediate information from ongoing branches, maintains a deduplicated query-level information pool, and broadcasts pool entries through the input context, allowing each branch in subsequent search steps to reuse discoveries made by other branches rather than rediscover the same information. Empirically, experiments on HMMT and AIME benchmarks show that CPT establishes a stronger accuracy--latency Pareto frontier than strong baselines across rollout budgets and model scales, highlighting search-time collaboration as an effective direction for efficient parallel TTS.