# 研究揭示 GPT-6 Astra 等前沿模型隐藏的思维链推理机制

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-22 08:00
- AIHOT 分数：47
- AIHOT 链接：https://aihot.news/items/cmufmdef905afro8wjnntc5ou
- 原文链接：https://arxiv.org/abs/2609.26637

## AI 摘要

研究者通过标准 API 注册自定义工具，成功诱导 GPT-6 Astra 等闭源前沿模型外化中间推理过程，提取出的推理在竞赛数学、科学和代码生成任务上与原生理性表现相当，并大幅超越无推理基线。分析显示 Astra 采用 token 高效的有向推理，更早选定正确路径，内部完成基础步骤，仅外化关键推理。

## 正文

The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-source systems are hidden. By registering a simple custom tool through a standard API feature, we induce frontier models to externalize intermediate reasoning. Because these traces may reflect post-hoc rationalization rather than genuine reasoning, we first evaluate against native CoT on open-source models and extend to closed-source frontier models including GPT-6 Astra. We find that the extracted reasoning matches native reasoning performance and substantially outperforms no-reasoning baselines, across competition mathematics, science, and code generation.

We then characterize how frontier models structure their intermediate reasoning. Across token efficiency, reasoning-step types, and induced reasoning trees, we identify systematic differences in how models externalize, compress, and organize reasoning. We find that Astra exhibits token-efficient directed reasoning, selecting a correct trajectory earlier, while resolving elementary steps internally and externalizing only crucial reasoning. These findings provide a behavioral lens on frontier-model reasoning beyond benchmark scores.