让大模型自主决定何时输出、何时思考，提升推理准确性与响应速度的平衡。
When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning
- 引入交错推理机制，允许模型在生成中混合私密推理与部分披露。
- 在两种模型和多个基准上，显著改善准确率与内容延迟的权衡表现。
- 适合需要高质量推理且关注响应节奏的智能系统研发者。
在单流自回归接口中，同一组标记既更新模型状态，又构成不可逆的公开承诺。这种耦合导致沉默成本：额外思考会推迟首个任务相关输出，而过早流式输出则可能引发提前承诺，影响后续生成。本文提出并行交错推理（SxS），将披露时机作为可控制决策融入标准自回归生成。SxS 在同一上下文中交错部分披露与持续私密推理，仅在推理充分支持时才释放内容。为学习该节奏而不鼓励冗余填充，我们通过匹配答案前缀与支撑推理前缀构建蕴含对齐的交错轨迹，再通过监督微调（SFT）获得双动作语义，强化学习（RL）恢复新格式下的推理性能。在两个Qwen3架构/规模（MoE Qwen3-30B-A3B，密集型 Qwen3-4B）及两个基准（领域内AIME25，领域外GPQA-Diamond）上，SxS在令牌级代理指标（如更新间等待时间）下均提升了准确率-内容延迟的帕累托优化效果。
原文摘要 · Abstract (English)
In single-stream autoregressive interfaces, the same tokens both update the model state and constitute an irreversible public commitment. This coupling creates a silence tax: additional deliberation postpones the first task-relevant content, while naive early streaming risks premature commitments that bias subsequent generations. We introduce Side-by-Side (SxS) Interleaved Reasoning, which makes disclosure timing a controllable decision within standard autoregressive generation. SxS interleaves partial disclosures with continued private reasoning in the same context, but releases content only when it is supported by the reasoning so far. To learn such pacing without incentivizing filler, we construct entailment-aligned interleaved trajectories by matching answer prefixes to supporting reasoning prefixes, then train with SFT to acquire the dual-action semantics and RL to recover reasoning performance under the new format. Across two Qwen3 architectures/scales (MoE Qwen3-30B-A3B, dense Qwen3-4B) and both in-domain (AIME25) and out-of-domain (GPQA-Diamond) benchmarks, SxS improves accuracy--content-latency Pareto trade-offs under token-level proxies such as inter-update waiting.
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。