让多个推理分支共享发现，减少重复探索，提升大模型推理效率。
Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling
- 各推理分支实时共享中间发现，构建去重信息池并广播给所有分支。
- 在HMMT和AIME上，相同计算量下准确率显著高于基线方法。
- 无需训练，适配不同模型规模，适合追求高效推理的开发者。
测试时扩展（TTS）通过分配额外推理计算来增强大语言模型的推理能力。然而，现有并行TTS方法在搜索过程中通常保持分支隔离：中间发现仅限本分支使用，无法实时指导其他分支。这种信息隔离导致大量重复探索，各分支反复发现已有信息，需更多搜索步数才能获取完整决策依据。为此，我们提出无需训练的推理框架——协同并行思维（CPT），实现并行分支间的搜索时信息共享。CPT从进行中的分支提取紧凑的中间信息，维护去重的查询级信息池，并将池中条目通过输入上下文广播，使后续搜索步骤中各分支可复用其他分支的发现，避免重复探索。实验表明，在HMMT与AIME基准上，CPT在不同回溯预算和模型规模下均建立更强的准确率-延迟帕累托前沿，验证了搜索时协作是高效并行TTS的有效方向。
原文摘要 · Abstract (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 \textbf{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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。