arXiv 论文：36,672 次重评分定位基础模型在双时序库存模拟中的错误来源
Where Should the Code Go? Locating Foundation-Model Errors in Bitemporal Inventory Simulation
做 Agent 或工作流的人常纠结：模型错了该改提示词、补代码还是加推理预算？这篇用 36,672 个可精确验证的库存模拟案例给出拆解，还发现强制工具调用接口会让 GPT-5.4 mini、DeepSeek V4 Pro 的推理评估失真，调接口和选模型的人都该看看。
一篇 arXiv 论文在一个可精确求解的 lost-sales 库存环境中，对 12 种闭源与开源模型配置、36,672 条独立重评分请求做受控诊断，回答一个工程问题：该改代码、该给更规范输入，还是该让模型多推理？环境基于双时序（事件发生时间与报告到达时间）的运营报告维护状态，再按给定情景向前推演。
实验采用协议在调用前冻结、强制答案调用接口作对照的设计。结果显示：规范化输入只消除报告选择错误，精确续写只消除推演错误，两者互不修复；哪种错误占主导随模型而异，强模型在原始报告上已接近上限；增加推理强度不是通用解药。
界面本身会混淆推理评估：强制答案调用下 GPT-5.4 mini 与 DeepSeek V4 Pro 高推理档会崩，而自动选择档位下则持平或更好；DeepSeek V4 Flash 在其自家 provider 上强制调用会关闭推理；gpt-oss 高档推理会耗尽输出预算。论文随发布放出全部请求，作为可复用的组件级诊断方法。
Where Should the Code Go? Locating Foundation-Model Errors in Bitemporal Inventory Simulation
Operational reports carry two clocks: when an event happened and when its report arrived; later reports can revise earlier ones. A foundation-model component that maintains the state supported by the reports visible at a cutoff, then rolls a supplied scenario forward, can be helped by exact code before it, after it or inside the call, or asked to reason harder. We ask which remedy removes which error, for which models, on an exactly solvable lost-sales inventory environment: 36,672 independently rescored requests over twelve configurations of closed and open-weight models, with a forced-answer-call interface as a control and protocols frozen before the calls. Weak models fail in separable ways. Canonical input removes report-selection error, exact continuation removes rollout error, neither repairs the other, and which error dominates differs by model; strong models are at ceiling on raw reports. Asking for more reasoning is no substitute and can depend on the interface: under a forced answer call high effort collapses GPT-5.4 mini and DeepSeek V4 Pro, which gain or hold under automatic choice; on its provider the forced call disables reasoning for DeepSeek V4 Flash; and at high effort gpt-oss exhausts its output budget. The contribution is a controlled component diagnostic, released with every request, and evidence that for some model and provider pairs the tool-calling interface confounds reasoning evaluation.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include GPT-5.4 mini, DeepSeek V4 Pro, gpt-oss, 推理模型.
Primary source verification: published directly by arXiv: DeepSeek with first-party authority.
