不值得再增加一个Token：面向高效深度研究智能体的边际价值估计

中文摘要 AI 辅助

长周期研究智能体通过迭代检索、聚合与合成解决开放性任务，但上下文会快速增长，而额外证据的边际价值往往会下降，这会导致不必要的Token开销、更高的延迟以及最终报告生成的输入噪声增加。我们研究深度研究智能体中用于上下文管理的边际价值估计，并首次对全流程各阶段的剪枝策略进行系统的阶段感知比较。我们在检索前、检索后、合成前阶段评估轻量级启发式准则和学习型价值模型。结果表明，剪枝效果更多取决于剪枝应用的位置，而非具体评分规则：早期剪枝可实现最大的端到端节省，而后期剪枝主要用于优化最终合成上下文。轻量级启发式方法可将Token使用量减少多达73%且几乎无质量下降，学习型剪枝在选定权衡上仍具竞争力，且没有单一方法在质量、效率和忠实度上占据主导地位。这些发现为设计高效的长周期智能体系统提供了实用指导。

英文摘要

Long-horizon research agents solve open-ended tasks through iterative retrieval, aggregation, and synthesis, but context grows rapidly while the marginal value of additional evidence often declines. This leads to unnecessary token cost, higher latency, and noisier inputs for final report generation. We study marginal value estimation for context management in deep research agents and present the first systematic stage-aware comparison of pruning strategies across the pipeline. We evaluate lightweight heuristic criteria and a learned value model at pre-retrieval, post-retrieval, and pre-synthesis stages. Our results show that pruning effectiveness depends more on where pruning is applied than on the specific scoring rule: early pruning yields the largest end-to-end savings, while later pruning mainly refines the final synthesis context. Lightweight heuristics reduce token usage by up to 73% with little quality degradation, learned pruning remains competitive on selected trade-offs, and no single method dominates across quality, efficiency, and faithfulness. These findings provide practical guidance for designing efficient long-horizon agentic systems.

发表机构

• University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
• The University of Texas at Austin（德克萨斯大学奥斯汀分校）
• Adobe Research（奥多比研究院）

机构由 AI 辅助整理，请以论文原文为准。