arXiv cs.CL· Lirui Luo, Kelong Mao, Xinwei Yang, Rongqing Li, Luyu Chen, Kieran Wong, Yudong Guo, Xinrui Wang, Jiayin Zhu, Gu Simiu, Sulong Xu, Cong Fang·· 10 小时前AI 评分38
CAMP-II：用在线策略蒸馏解锁预训练文件操作能力，提升编码智能体长程任务记忆
Coding Agent Memory Post-Training II: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via On-Policy Distillation
AI 导读
CAMP-II 通过全异步在线策略蒸馏，让单一策略在 CAMG-II 的 Shop、Coding、AutoResearch、General、Visual 五个长程环境中联合训练，学习基于文件的记忆行为。在 CAMG-II 上，其收益达到最强 OPD 基线的 2.97 倍，所学记忆行为还泛化到 Terminal-Bench 2.1 和 SWE-Bench Pro V2 两个外部基准并提升成功率。
正文 · 原文
Authors:Lirui Luo, Kelong Mao, Xinwei Yang, Rongqing Li, Luyu Chen, Kieran Wong, Yudong Guo, Xinrui Wang, Jiayin Zhu, Gu Simiu, Sulong Xu, Cong Fang
Abstract:Language-model agents increasingly tackle long-horizon tasks whose interaction histories exceed the model's active context. They must therefore decide what to write down and what to read back, and when to do either. Recent work has begun to use on-policy distillation (OPD) to make memory control part of the policy, relying on memory tools and compaction protocols that lie outside either model's pre-training. However, this weakens the distillation on both sides: the teacher cannot give useful guidance on an interface it has never used, and the student samples too few meaningful memory actions for that guidance to take effect. To study this problem, we introduce Coding Agent Memory Gym II (CAMG-II), a suite of long-horizon agentic-RL environments spanning Shop, Coding, AutoResearch, General, and Visual. Alongside each environment's native task interface, CAMG-II provides ordinary Bash access and an episode-persistent workspace, enabling the policy to create, revise, search, and reuse files as memory across context replacements. We also introduce Coding Agent Memory Post-Training II (CAMP-II), which trains a single policy jointly across all five environments with fully asynchronous OPD to learn this file-based memory behavior directly from a frozen teacher with a prior for file operations. On CAMG-II, CAMP-II obtains 2.97 times the gain of the strongest OPD baseline. The memory behavior CAMP-II learns generalizes to two external benchmarks, Terminal-Bench 2.1 and SWE-Bench Pro V2, with improved success rates.
| Comments: | 40 pages, 6 figures, 8 tables |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.14009 [cs.LG] |
| (or arXiv:2611.14009v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14009 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lirui Luo [view email]
[v1]
Tue, 10 Nov 2026 12:49:24 UTC (11,663 KB)
来源：arXiv cs.CL · arxiv.org