arXiv：cs.LG· Youngbin Choi, Sehyun Hwang, Suhyeon Jun, Seoyeon Lee, Sunghyun Choi, MoonJeong Park, Dongwoo Kim·· 3 小时前
多会话 LLM 智能体换模型后行为会迁移：DASH 摘要法可保留强模型行为
New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents
AI 导读
多会话 LLM 智能体切换模型时会出现「行为迁移」：接收方倾向沿用生成其历史的模型的推理与行动模式，原始历史直接传递时最明显，摘要化可大幅削弱。为此提出的 Direction- and Authorship-aware Summarization of History（DASH）在保留更强模型行为的同时减少弱到强的迁移。重复切换实验显示 DASH 优于原始历史传递和朴素摘要基线。
正文
Abstract:Multi-session agents can switch between LLMs to balance performance and inference cost. Such switches require transferring a history for continuity, yet their effects on the recipient remain underexplored. Through controlled experiments with multi-session tasks, we uncover behavior transfer: recipients tend to adopt reasoning and action patterns from the models that generated their histories. This effect is most evident with raw-history transfer but is substantially reduced by summarization. Based on these findings, we propose Direction- and Authorship-aware Summarization of History (DASH) that preserves stronger-model behavior while minimizing weak-to-strong transfer via summarization. Experiments with repeated swaps show that DASH outperforms raw-history transfer and naive summarization baselines. These results suggest that effective multi-model orchestration requires considering not only which model to use, but also which behavioral patterns to carry forward.
| Comments: | 27 pages |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.19712 [cs.LG] |
| (or arXiv:2610.19712v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19712 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Youngbin Choi [view email]
[v1]
Wed, 14 Oct 2026 07:38:54 UTC (1,755 KB)
来源：arXiv：cs.LG · arxiv.org