Large language models increasingly serve as execution engines for agentic systems, yet they still consume context through a sequential text interface. This creates a mismatch with modern structured agent workflows, in which independent branches explore subtasks, retrieve evidence, or generate candidate solutions before a final synthesis step. Existing systems typically merge these branches by concatenating their textual outputs, which discards the parallel structure and incurs redundant prefill computation. In this work, we introduce Parallel-Synthesis, a plug-and-play framework that enables a synthesizer to directly consume the KV caches produced by parallel worker agents. Parallel-Synthesis combines a cache mapper that calibrates independently generated branch caches with a fine-tuned synthesizer adapter that enables generation from this non-sequential cache interface. We train Parallel-Synthesis using data that exposes the synthesizer to parallel cache contexts, teaches aggregation across cached branches, and distills reasoning behavior from standard text-concatenation-based synthesis. Across nine downstream datasets spanning math, science QA, code generation, GAIA, and multi-agent database diagnosis, Parallel-Synthesis matches or outperforms text-based synthesis on seven datasets and remains close on the other two. It also reduces time-to-first-token by 2.5x-11x, suggesting that direct cache-based synthesis is a promising interface for more native and efficient synthesis over parallel agent branches.

翻译：大语言模型日益成为智能体系统的执行引擎，但仍通过序列化文本接口消耗上下文，这与现代结构化智能体工作流形成矛盾——在后者中，独立分支并行执行子任务、检索证据或生成候选方案，最终进行汇总合成。现有系统通常通过拼接各分支的文本输出来合并，这不仅丢失了并行结构，还导致冗余的预填充计算。本文提出并行合成框架（Parallel-Synthesis），一种即插即用的方案，使合成器能直接消费并行工作智能体产生的KV缓存。该框架结合缓存映射器（校准独立生成的分支缓存）与微调合成适配器（支持从非序列缓存接口进行生成）。我们使用暴露合成器于并行缓存上下文的数据训练并行合成框架，教授跨缓存分支的聚合技术，并蒸馏自标准文本拼接式合成的推理行为。在涵盖数学、科学问答、代码生成、GAIA及多智能体数据库诊断的九个下游数据集上，并行合成框架在七个数据集中达到或超越基于文本的合成效果，在其余两个数据集中表现接近。同时，首令牌生成时间降低2.5-11倍，表明基于缓存的直接合成是应对并行智能体分支更原生、高效的合成接口。