智能体学习其运行时：解释器持久性作为训练时语义
Evaluating Agents Across Runtime Contracts: When Mismatch Costs Efficiency or Quality
AI总结：
研究探讨解释器持久性对智能体学习的影响，发现其影响解决方案达成方式而非能否达成，且训练与运行时对齐可提升效率。
摘要：
工具增强的大型语言模型越来越多地被部署为智能体，这些智能体在自然语言推理和可执行Python操作之间交替进行，如CodeAct风格的框架。在部署过程中，这些智能体依赖于在步骤之间持续的运行时状态。相比之下，用于后训练这些模型的轨迹很少编码如何管理解释器状态。我们询问解释器持久性是否仅仅是运行时的支架，还是训练数据中的属性，影响智能体如何学习使用解释器。我们隔离状态持久性作为训练时的变量。我们引入了Opaque Knapsack，一种程序生成的部分可观测优化任务家族，旨在防止单次解决方案。项目属性和约束隐藏在预算化的工具调用背后，迫使多轮控制流和迭代状态修订。在保持任务实例、提示、工具、模型和监督固定的情况下，我们生成匹配的轨迹，仅在解释器状态在步骤之间持续或在每个动作后重置时有所不同。然后，我们对每个轨迹变体微调相同的基模型（Qwen3-8B），并评估所有四种训练-运行时组合。我们的2x2交叉评估显示，解释器持久性影响智能体如何达到解决方案，而不是是否能够达到：解决方案质量在统计上在不同条件下无法区分，但令牌成本和稳定性差异显著。在无状态运行时中训练的模型在约80%的回合中触发缺少变量错误；在无状态运行时中训练的模型在持久运行时中冗余地重新推导保留的状态，使用约3.5倍更多的令牌。解释器持久性应被视为智能体轨迹的首要语义。对微调数据与部署运行时对齐可以提高效率，并减少脆弱的训练-运行时不匹配。
英文摘要：
In CodeAct, language-model agents write Python that calls tools and use execution feedback to choose actions. Persistent runtimes preserve Python variables between actions; stateless runtimes clear them without resetting task progress. Training traces demonstrate task-solving strategies and runtime-specific ways to store and recover intermediate results. We study runtime transfer: whether agents trained under one contract remain effective under the other, a dependence that fixed-runtime evaluations can conceal. Across three tasks requiring a working record built from tool feedback, we fine-tune separate Qwen3-8B agents per task and runtime on instance-paired persistent and stateless traces and evaluate all four training-deployment combinations. We vary the per-turn tool-call cap: how many calls one Python action may execute. In our primary task, agents inspect hidden item attributes and select a high-value subset under a weight limit. At 80 calls per turn, a persistent-trained agent deployed statelessly scores 0.61 of optimal value against 0.77 under matched persistent deployment, but uses 4.4 times as many tokens rebuilding its record. Tightening the cap to 25 reduces mismatched quality to 0.07 while matched quality remains 0.66. Trace replay shows that the cap interrupts inspection, the reset erases the partial record, and rebuilding consumes calls needed for progress. The widening gap replicates across training seeds, a second rollout, and two additional base models. Across the settings studied, cap tightening produces a mismatch-specific collapse only where interruptions are frequent and matched execution resumes while mismatched execution restarts. Evaluations of trace-fine-tuned agents should specify episode limits, test runtime transfer across caps, and report cost alongside quality; otherwise, the same mismatch may appear as redundant computation or near-total quality loss.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
