Metraipolis › archive › dc_a6fc4aa635fb
MemRole: From Memories to Decisions for Long-Horizon Reasoning in Role-Playing Agents — arXiv:2611.01778
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01778
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:18:11.647Z
- SHA-256 of the archived text
f2fe7941cf8fe6de5663cbe87d2f245b6e1f2f86eb2ea1b3705b43d40c999e4b- Stable URL of this page
https://metraipolis.com/documento/dc_a6fc4aa635fb
How to cite
MemRole: From Memories to Decisions for Long-Horizon Reasoning in Role-Playing Agents — arXiv:2611.01778 — arXiv (en), https://arxiv.org/abs/2611.01778 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6fc4aa635fb (Metraipolis archive dc_a6fc4aa635fb, sha256 f2fe7941cf8fe6de5663cbe87d2f245b6e1f2f86eb2ea1b3705b43d40c999e4b)
BibTeX
@misc{dca6fc4aa635fb,
title = {MemRole: From Memories to Decisions for Long-Horizon Reasoning in Role-Playing Agents — arXiv:2611.01778},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01778},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6fc4aa635fb; sha256 f2fe7941cf8fe6de5663cbe87d2f245b6e1f2f86eb2ea1b3705b43d40c999e4b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01778. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM-based role-playing agents are fluent at imitating a character's style, yet struggle to make role-consistent decisions over long narrative horizons. Such decisions are shaped by experiences spanning many prior scenes, which are often partial and may point in different directions. Existing methods inject cross-scene memories as context, but do not reason about how past events shape a character's current motivations and behavior. We propose MemRole, a framework that makes this memory-to-decision process explicit. It introduces Long-Horizon Memory Thinking (LHMT), a reasoning schema that decomposes hidden reasoning into context understanding, memory activation, and response strategy planning, trained on a novel-derived dataset whose character-grounded, timeline-constrained memory pools limit each character to what it could plausibly know at the current narrative point. Beyond supervised fine-tuning, we propose Self-Refining On-Policy Self-Distillation (SR-OPSD): the model critiques its own rollouts against the reference under a data-driven rubric, and a critique-conditioned teacher view of the same model distills token-level guidance back into the policy. MemRole-32B improves over its backbone by 15.2 points on memory-grounded role-playing, performs on par with frontier LLMs such as GPT-5.4, and achieves the best character-motivation recognition accuracy on CroSS-MR. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.01778 — 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 2026-11-03T18:09:53.627Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).