Metraipolis › archive › dc_ade05bff415b
RIPPLE: Recovery Internalization through Process-Level Policy Learning and Effect-Aware Credit for Long-Horizon Agentic Coding — arXiv:2610.31276
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31276
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T20:53:22.577Z
- SHA-256 of the archived text
e751d2b6e811e65d09831ffcf1f2e737d7b9fdc3acc6c7412baf6b46f081a3a6- Stable URL of this page
https://metraipolis.com/documento/dc_ade05bff415b
How to cite
RIPPLE: Recovery Internalization through Process-Level Policy Learning and Effect-Aware Credit for Long-Horizon Agentic Coding — arXiv:2610.31276 — arXiv (en), https://arxiv.org/abs/2610.31276 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ade05bff415b (Metraipolis archive dc_ade05bff415b, sha256 e751d2b6e811e65d09831ffcf1f2e737d7b9fdc3acc6c7412baf6b46f081a3a6)
BibTeX
@misc{dcade05bff415b,
title = {RIPPLE: Recovery Internalization through Process-Level Policy Learning and Effect-Aware Credit for Long-Horizon Agentic Coding — arXiv:2610.31276},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31276},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ade05bff415b; sha256 e751d2b6e811e65d09831ffcf1f2e737d7b9fdc3acc6c7412baf6b46f081a3a6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31276. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.31276 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-25T20:47:56.924Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).