Metraipolis › archive › dc_7ac0ea5e92eb

A Graph-Based Reinforcement Learning Framework for Structured Drift Diagnosis and Recovery in Autonomous LLM Agents — arXiv:2608.14109

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.14109
License (as archived): CC0-1.0
Archived: 2026-10-19T02:19:31.492Z
SHA-256 of the archived text: 8f63dc22376c948f0c981874c9585f98a866bb83a43eb1de7468ba475f0d6b81
Stable URL of this page: https://metraipolis.com/documento/dc_7ac0ea5e92eb

How to cite

A Graph-Based Reinforcement Learning Framework for Structured Drift Diagnosis and Recovery in Autonomous LLM Agents — arXiv:2608.14109 — arXiv (en), https://arxiv.org/abs/2608.14109 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ac0ea5e92eb (Metraipolis archive dc_7ac0ea5e92eb, sha256 8f63dc22376c948f0c981874c9585f98a866bb83a43eb1de7468ba475f0d6b81)

BibTeX

@misc{dc7ac0ea5e92eb,
  title = {A Graph-Based Reinforcement Learning Framework for Structured Drift Diagnosis and Recovery in Autonomous LLM Agents — arXiv:2608.14109},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14109},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ac0ea5e92eb; sha256 8f63dc22376c948f0c981874c9585f98a866bb83a43eb1de7468ba475f0d6b81},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14109. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous LLM agents are increasingly deployed in complex real-world workflows, yet they remain vulnerable to runtime behavioral drift, a silent deviation from the original task that can lead to irreversible side effects on external systems. Existing approaches address drift at the prompt level but lack structured mechanisms for step-level detection, risk assessment, and recovery decision. Because the main task-executing agent is often a large and expensive model that cannot be re-trained on every deployment, this work targets a plug-and-play recovery module instead. It introduces a graph-based framework in which a single small language model is trained via reinforcement learning to specialize at each node of a recovery graph, external to the main agent. Each node has a precise role\,: drift classification, operation detection, risk evaluation, or final decision and the model learns to produce structured XML-formatted reasoning adapted to that role. Training combines rule-based structural rewards with an LLM-as-judge semantic-quality signal, so that the model is graded both on how it answers (schema and length) and on what it says. Experiments on the public AppWorld benchmark show that the method generally exploits information about the suspected drift onset to issue correct recovery decisions using a small language model. In addition, the trained small language model reliably respects the prescribed output schema and produces semantically appropriate content in each field according to its assigned node role.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.14109 — 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 2026-10-19T02:01:30.018Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).