arXiv cs.AI· Jingxuan Xu, Zihang Xu, Yuechen Luo, Ziqi Miao, Wenqiang Zhu, Weihao Li, Junhao Fan, Xinshun Feng, Zhiyi Lai, Yanan Wu, Haoyang Huang, Ken Deng·· 2 小时前AI 评分38
RIPPLE:面向长程智能体编码的过程级策略学习与效果感知信用分配恢复训练框架
RIPPLE: Recovery Internalization through Process-Level Policy Learning and Effect-Aware Credit for Long-Horizon Agentic Coding
AI 导读
arXiv 论文提出 RIPPLE,一种面向恢复的训练框架,针对长程编码智能体“能产生批评却仍沿用错误轨迹”的 Critique-to-Action Handoff Gap,将过程级引导内化到单一自恢复策略中。
正文 · 原文
Authors:Jingxuan Xu, Zihang Xu, Yuechen Luo, Ziqi Miao, Wenqiang Zhu, Weihao Li, Junhao Fan, Xinshun Feng, Zhiyi Lai, Yanan Wu, Haoyang Huang, Ken Deng
Abstract:Long-horizon coding agents can observe a failure and generate a plausible critique yet continue along the same incorrect trajectory. We call this the Critique-to-Action Handoff Gap. We introduce RIPPLE, a recovery-oriented training framework that internalizes process-level guidance into a single self-recovering policy. A prefix-only teacher provides evidence-grounded recovery supervision without access to future actions or terminal outcomes. After lightweight distillation, reinforcement learning assigns stage-specific credit to reflection triggering, diagnosis, and corrective action. Local validity signals gate trajectory advantages so that intermediate recovery decisions do not indiscriminately inherit terminal outcomes. Across four repository-level software-engineering benchmarks, RIPPLE improves the base policy by an arithmetic mean of 4.8 score points, with no auxiliary critic at deployment. Controlled ablations isolate the benefits of local, stage-aligned credit, and matched-prefix interventions show that critique semantics affect subsequent correction. Recovery gains concentrate where the prefix contains sufficient diagnostic evidence and the repository state remains reversible within the remaining budget.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.31276 [cs.AI] |
| (or arXiv:2610.31276v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31276 arXiv-issued DOI via DataCite |
Submission history
From: Miao Ziqi [view email]
[v1]
Thu, 22 Oct 2026 13:45:33 UTC (5,439 KB)
[v2]
Tue, 17 Nov 2026 09:53:25 UTC (5,441 KB)
来源:arXiv cs.AI · arxiv.org