RE-TRAC：面向深度搜索代理的递归轨迹压缩技术

摘要

基于大语言模型的深度研究智能体主要构建在ReAct框架之上。这种线性设计难以回溯早期状态、分支探索替代方向或在长上下文下保持全局认知，常导致局部最优、冗余探索和低效搜索。我们提出Re-TRAC智能体框架，通过在每个轨迹后生成结构化状态表征来总结证据、不确定性、失败案例及未来计划，并使后续轨迹基于该状态表征进行条件化执行，从而实现跨轨迹探索。该框架支持迭代式反思与全局知情规划，将研究重构为渐进式过程。实验结果表明，在BrowseComp基准测试中，Re-TRAC使用前沿大语言模型时持续优于ReAct框架15-20%。针对小规模模型，我们引入Re-TRAC感知的监督微调方法，在同等规模下实现了最先进性能。值得注意的是，Re-TRAC在多轮迭代中呈现工具调用次数和令牌使用量的单调递减，表明其通过跨轨迹反思驱动了渐进式目标探索，而非冗余搜索。

English

LLM-based deep research agents are largely built on the ReAct framework. This linear design makes it difficult to revisit earlier states, branch into alternative search directions, or maintain global awareness under long contexts, often leading to local optima, redundant exploration, and inefficient search. We propose Re-TRAC, an agentic framework that performs cross-trajectory exploration by generating a structured state representation after each trajectory to summarize evidence, uncertainties, failures, and future plans, and conditioning subsequent trajectories on this state representation. This enables iterative reflection and globally informed planning, reframing research as a progressive process. Empirical results show that Re-TRAC consistently outperforms ReAct by 15-20% on BrowseComp with frontier LLMs. For smaller models, we introduce Re-TRAC-aware supervised fine-tuning, achieving state-of-the-art performance at comparable scales. Notably, Re-TRAC shows a monotonic reduction in tool calls and token usage across rounds, indicating progressively targeted exploration driven by cross-trajectory reflection rather than redundant search.

RE-TRAC：面向深度搜索代理的递归轨迹压缩技术

RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents

摘要

Support