# 多轮长程规划能力从预训练到后训练：单/多教师在线智能体蒸馏研究

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-07-27 08:00
- AIHOT 分数：44
- AIHOT 链接：https://aihot.virxact.com/items/cms46i53v0083roepp1zb1m42
- 原文链接：https://arxiv.org/abs/2607.24720

## AI 摘要

一项研究通过统一可控的多轮环境，系统分析了基础模型智能体在预训练、GRPO/OPD后训练及多教师在线蒸馏（MOPD）三个阶段的长程规划能力获取与整合。研究发现：显式世界模型构建通过CoT状态转换建模可增强长程泛化；低质量轨迹因误差随长程放大而严重损害性能；OPD在低质量长程场景下比GRPO具有更广的有效区域；MOPD通过收敛至共享规划模式实现跨环境泛化，而完全冲突的模式会导致严重干扰。

## 正文

Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains unclear. Existing models are trained on uncontrollable and opaque Internet data, making it difficult to identify how planning ability is acquired, shaped, and integrated. To address this challenge, we introduce a unified and controlled multi-turn environment that enables precise control. It allows systematically study long-horizon planning across three stages. (1) Planning ability acquisition during pre-training. We study data format, distribution, and quality. Explicit world model construction through CoT state transition modeling yields stronger long-horizon generalization. Atomic skills alone are insufficient for compositional generalization, whereas a litte long-horizon data works. Moreover, suboptimal trajectories severely impair performance because errors amplify over long horizons. (2) Planning ability shaping via GRPO and OPD post-training. Through mutual information, we distinguish general planning patterns from task-specific planning knowledge. For planning patterns, we identify three application regions of post-training: unnecessary, effective, and unsupported. OPD has a broader effective region than GRPO under low-quality and long-horizon settings, as it provides more consistent update directions. For planning knowledge, distilling unseen procedures from a teacher with different knowledge may impair student's prior world modeling without fully establishing new knowledge. (3) Planning ability integration through MOPD post-training. We show that multi-teacher on-policy distillation (MOPD) integrates capabilities by converging to shared planning-pattern across environments. Compatible patterns enable cross-environment generalization, partially shared patterns support continual learning, while completely conflicting patterns cause severe interference.